© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1267
    Prev
    Next
    INDEX
    Explanations

    phrases about professional accomplishments, organizations, and recruiting.

    oai_token-act-pair · gemini-2.0-flash

    famous/known names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    LookAnd
    -1.00
    webElementXpaths
    -0.96
     propOrder
    -0.92
     وتسجيلات
    -0.91
    الحياه
    -0.85
    typeorm
    -0.84
    MigrationBuilder
    -0.83
    GenerationType
    -0.82
    parsedMessage
    -0.81
    ViewImports
    -0.81
    POSITIVE LOGITS
     famous
    0.76
     known
    0.74
     name
    0.71
    name
    0.69
    known
    0.67
    有名
    0.65
     named
    0.65
     names
    0.64
     извест
    0.62
     big
    0.60
    Activations Density 1.293%

    No Known Activations