© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14564
    Prev
    Next
    INDEX
    Explanations

    symbols, parentheses, and abbreviations related to scientific studies and results

    oai_token-act-pair · gemini-2.0-flash

    specialized scientific terminology or jargon

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Factbook
    -0.46
     Alright
    -0.46
     orari
    -0.45
     propres
    -0.45
     goutte
    -0.44
    unuz
    -0.44
     vuotta
    -0.43
    Voir
    -0.43
     testigos
    -0.42
     endroits
    -0.42
    POSITIVE LOGITS
    tvguidetime
    0.96
    DockStyle
    0.75
    ^(@)
    0.73
    RuleContext
    0.72
    IndentedString
    0.69
     himſelf
    0.69
     itſelf
    0.68
    SequentialGroup
    0.65
     theſe
    0.64
     poffible
    0.64
    Activations Density 4.210%

    No Known Activations