© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13620
    Prev
    Next
    INDEX
    Explanations

    scientific writing with results or names mentioned

    oai_token-act-pair · gemini-2.0-flash

    scientific evidence

    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
    RenderAtEndOf
    -0.85
    LookAnd
    -0.76
    elemField
    -0.76
    Says
    -0.73
     Efq
    -0.71
    ModelSerializer
    -0.66
     ſever
    -0.66
     Requested
    -0.65
     Diſ
    -0.65
    ContentAlignment
    -0.64
    POSITIVE LOGITS
     ind
    0.60
     Ind
    0.57
    Ind
    0.56
     inf
    0.54
    indi
    0.49
     IND
    0.49
     indi
    0.46
    ind
    0.46
    chappement
    0.44
     Numerade
    0.44
    Activations Density 1.618%

    No Known Activations