© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3187
    Prev
    Next
    INDEX
    Explanations

    lines of code in an Android application

    oai_token-act-pair · gemini-2.0-flash

    layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AllAfrica
    -0.68
    annica
    -0.65
    ----+
    -0.65
    Demikian
    -0.63
     textStatus
    -0.63
     للمعارف
    -0.63
    addPreferredGap
    -0.63
    èdia
    -0.61
    InSection
    -0.61
    ---+
    -0.61
    POSITIVE LOGITS
    rrggbb
    0.64
    SourceChecksum
    0.52
    ↵
    0.52
    Migrations
    0.52
    ↵↵
    0.49
    '
    0.49
    setVerticalGroup
    0.49
    EXACT
    0.46
     formule
    0.46
    1
    0.44
    Activations Density 0.142%

    No Known Activations