© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12643
    Prev
    Next
    INDEX
    Explanations

    mathematical, programming, and foreign language code

    oai_token-act-pair · gemini-2.0-flash

    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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     فريبيس
    -0.73
    principalTable
    -0.59
     المعيارى
    -0.59
    Rohy
    -0.58
    DoubleQuotes
    -0.57
    memoized
    -0.57
     tayo
    -0.56
    annica
    -0.53
     dong
    -0.53
     متعلقه
    -0.52
    POSITIVE LOGITS
    niejszy
    0.55
     prowadzi
    0.54
    niczy
    0.54
    )||
    0.54
    Бы
    0.53
    łoży
    0.52
     עש
    0.51
     поня
    0.51
     شدید
    0.50
    دانشنامهٔ
    0.49
    Activations Density 1.656%

    No Known Activations