© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12862
    Prev
    Next
    INDEX
    Explanations

    bullet points, numbered lists, and question/answer formats

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ;
    -0.62
    ,
    -0.61
     they
    -0.59
     them
    -0.59
     him
    -0.57
     their
    -0.57
     then
    -0.54
     amongst
    -0.54
     among
    -0.53
     competition
    -0.53
    POSITIVE LOGITS
     stället
    0.88
     The
    0.81
    — 
    0.79
    ]^{-
    0.76
    ?».
    0.71
     ProtoMessage
    0.71
    )».
    0.70
     On
    0.69
     For
    0.69
    '],
    0.68
    Activations Density 6.138%

    No Known Activations