© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    what appears to be code and/or identifiers

    oai_token-act-pair · gemini-2.0-flash

    code/technical text

    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
    ding
    -0.82
    kháu
    -0.82
    dly
    -0.82
    UserScript
    -0.79
     StatelessWidget
    -0.78
     فريبيس
    -0.77
    doria
    -0.77
    AnchorStyles
    -0.76
    dings
    -0.76
    dap
    -0.76
    POSITIVE LOGITS
    t
    0.52
    ac
    0.47
    yn
    0.46
    at
    0.44
    r
    0.44
    tal
    0.43
    app
    0.41
    re
    0.41
    ob
    0.41
    y
    0.40
    Activations Density 0.947%

    No Known Activations