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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12410
    Prev
    Next
    INDEX
    Explanations

    words related to bicycle tire repair

    oai_token-act-pair · gemini-2.0-flash

    specific technical terms and functionalities

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

    technical support questions and answers

    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
     “
    -0.56
    Its
    -0.54
    of
    -0.54
     Z
    -0.52
     
    -0.52
     P
    -0.51
     We
    -0.50
     "
    -0.50
    We
    -0.49
     G
    -0.49
    POSITIVE LOGITS
    ChildScrollView
    0.93
     the
    0.91
    RenderAtEndOf
    0.86
    tagHelperRunner
    0.81
    IUrlHelper
    0.81
    StoryboardSegue
    0.78
     Donde
    0.78
     الحره
    0.78
    новништво
    0.76
     للاسماء
    0.76
    Activations Density 3.121%

    No Known Activations