© 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. 5349
    Prev
    Next
    INDEX
    Explanations

    code for batting statistics

    oai_token-act-pair · gemini-2.0-flash

    code statistics

    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
    AddTagHelper
    -0.85
     autorytatywna
    -0.81
    DockStyle
    -0.80
    IntoConstraints
    -0.80
     مشين
    -0.77
     AssemblyCulture
    -0.76
    InputBorder
    -0.75
     ExecuteAsync
    -0.75
    webElementXpaths
    -0.75
     jScrollPane
    -0.73
    POSITIVE LOGITS
     off
    0.57
     runs
    0.47
    strix
    0.47
    økt
    0.41
    球
    0.41
    起
    0.37
     frente
    0.36
    digt
    0.36
     Encuentra
    0.36
    Off
    0.35
    Activations Density 0.403%

    No Known Activations