© 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. 12493
    Prev
    Next
    INDEX
    Explanations

    articles followed by adjectives describing something, along with related words like "reader".

    oai_token-act-pair · gemini-2.0-flash

    shot

    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
    LError
    -0.54
    SIN
    -0.49
    iciais
    -0.48
    ramienta
    -0.47
    gpg
    -0.45
     فريبيس
    -0.45
     sartén
    -0.44
    heer
    -0.44
    switch
    -0.44
    ector
    -0.44
    POSITIVE LOGITS
     shot
    0.93
     Shot
    0.85
    Shot
    0.83
     SHOT
    0.81
    shot
    0.81
    makeConstraints
    0.77
     pick
    0.74
    SHOT
    0.73
     face
    0.71
    face
    0.70
    Activations Density 1.318%

    No Known Activations