© 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. 16305
    Prev
    Next
    INDEX
    Explanations

    c code including struct, function, variables and conditional statements

    oai_token-act-pair · gemini-2.0-flash

    C code

    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
    ագրություններ
    -0.90
    IntoConstraints
    -0.89
    aarrggbb
    -0.85
     للمعارف
    -0.82
    webElementXpaths
    -0.81
     שוליים
    -0.80
     okuyayım
    -0.80
    +#+
    -0.79
     незавершена
    -0.79
    FXMLLoader
    -0.79
    POSITIVE LOGITS
    jazd
    0.53
    F
    0.48
     mier
    0.42
    jazdu
    0.39
    frid
    0.39
    if
    0.38
     poseen
    0.38
    fra
    0.38
    5
    0.37
    assi
    0.36
    Activations Density 2.445%

    No Known Activations