© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15093
    Prev
    Next
    INDEX
    Explanations

    words related to planning, coordination, and implementation of programs, especially those that use a step-by-step approach.

    oai_token-act-pair · gemini-2.0-flash

    descriptors indicating suitability or effectiveness

    np_token-act-pair-logits · gpt-4o-mini

    positive attributes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.77
    sizeCache
    -0.57
     ujednoznacz
    -0.56
    ::_('
    -0.55
    Хьажоргаш
    -0.54
    mybatisplus
    -0.54
    FirebaseDatabase
    -0.54
    хьтан
    -0.53
     <>",
    -0.53
    Referanser
    -0.52
    POSITIVE LOGITS
     appropriate
    0.81
     strong
    0.78
     a
    0.74
     effective
    0.74
     Appropriate
    0.73
     suitable
    0.71
     proper
    0.71
     clear
    0.70
    Appropriate
    0.69
     efficient
    0.69
    Activations Density 2.919%

    No Known Activations