© 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. 13957
    Prev
    Next
    INDEX
    Explanations

    news articles/reports

    oai_token-act-pair · gemini-2.0-flash

    words related to denial

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

    variations of deny

    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
     purpoſe
    -0.81
    mybatisplus
    -0.78
    parsedMessage
    -0.75
    AndEndTag
    -0.70
     Houſe
    -0.68
     houſe
    -0.67
     itſelf
    -0.66
     pleaſure
    -0.66
     Theſe
    -0.64
     ſeveral
    -0.63
    POSITIVE LOGITS
     deny
    2.44
     denied
    2.36
     denial
    2.22
     denies
    2.11
     denying
    2.11
    denied
    1.81
     Denial
    1.78
    denial
    1.77
    deny
    1.73
     Denied
    1.70
    Activations Density 2.947%

    No Known Activations