© 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. 12847
    Prev
    Next
    INDEX
    Explanations

    the string "av" even as a prefix or with separators

    oai_token-act-pair · gemini-2.0-flash

    av

    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
     kaynağından
    -0.62
    forKey
    -0.58
    setopt
    -0.51
    !("{
    -0.51
    yden
    -0.51
    GeneratedCode
    -0.50
    FieldBuilder
    -0.50
    geben
    -0.49
    lapsingToolbar
    -0.49
    ścia
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.58
    Aholisi
    0.52
     AspNetCore
    0.50
    DoubleQuotes
    0.49
     passada
    0.49
     Akismet
    0.49
    PreExecute
    0.48
     FetchType
    0.46
    ocratic
    0.45
     parlando
    0.45
    Activations Density 0.426%

    No Known Activations