© 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. 9427
    Prev
    Next
    INDEX
    Explanations

    a mix of portuguese words and some html button markup

    oai_token-act-pair · gemini-2.0-flash

    programming and coding terminology

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

    Non-English computer code

    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
    NOPQRST
    -0.60
    Gön
    -0.54
    webElementXpaths
    -0.52
    WriteBarrier
    -0.52
     voks
    -0.50
     ImportError
    -0.50
     herself
    -0.47
     toppen
    -0.47
    DoubleQuotes
    -0.47
    WithIdentifier
    -0.46
    POSITIVE LOGITS
    migrationBuilder
    0.58
    GIVEREF
    0.52
     sinc
    0.52
     */;
    0.50
     discharged
    0.49
    Scénario
    0.49
    IntentFilter
    0.49
     سكانية
    0.49
     Référence
    0.48
    */;
    0.48
    Activations Density 0.360%

    No Known Activations