© 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. 16302
    Prev
    Next
    INDEX
    Explanations

    code that creates dialog boxes

    oai_token-act-pair · gemini-2.0-flash

    Unusual symbols/characters

    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
    ScopeManager
    -0.75
    WriteBarrier
    -0.69
     snippetHide
    -0.69
    ActionCreators
    -0.69
    +:+
    -0.65
     Efq
    -0.64
    EndGlobalSection
    -0.64
     propOrder
    -0.64
    UserScript
    -0.63
    šanās
    -0.60
    POSITIVE LOGITS
    ⓘ
    0.58
     Drapeau
    0.48
     comb
    0.45
    }{*}{
    0.44
    !*\
    0.43
     *)__
    0.41
    Демографія
    0.40
    aarrggbb
    0.39
     pří
    0.39
    MathML
    0.39
    Activations Density 0.226%

    No Known Activations