© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 16304
    Prev
    Next
    INDEX
    Explanations

    abbreviations and other shorthand, or specific letters

    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
     onOptions
    -0.82
     AspNetCore
    -0.80
     Paglinawan
    -0.79
    )];
    
    -0.65
    %";
    -0.60
    PageRoute
    -0.60
    __).
    -0.58
    ftagPool
    -0.57
    InitStruct
    -0.56
    !")
    
    -0.56
    POSITIVE LOGITS
    .,
    1.53
    .:
    1.26
    .-
    1.18
    .;
    1.16
    ./
    1.05
    .)
    1.05
    .—
    1.03
    .!
    1.02
    .'
    1.01
    .+
    1.01
    Activations Density 2.430%

    No Known Activations