© 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. 2237
    Prev
    Next
    INDEX
    Explanations

    a mix of Russian words primarily related to website development and shopping

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating actions or states

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

    verbs

    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
     ModelExpression
    -0.95
     للمعارف
    -0.82
     pleaſure
    -0.82
     itſelf
    -0.81
     Theſe
    -0.79
     estekak
    -0.78
    ſelves
    -0.76
     theſe
    -0.75
     houſe
    -0.74
    ⓧ
    -0.74
    POSITIVE LOGITS
     goes
    0.67
     has
    0.64
     appears
    0.63
     becomes
    0.59
     receives
    0.59
     takes
    0.58
     allows
    0.56
     comes
    0.55
     refers
    0.55
     includes
    0.54
    Activations Density 0.844%

    No Known Activations