© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4673
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially those used in conditional statements.

    oai_token-act-pair · gemini-2.0-flash

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    -0.89
     NSCoder
    -0.79
     nahilalakip
    -0.77
    LinkId
    -0.72
    Hauptartikel
    -0.71
     الاطلاع
    -0.69
    Diweddarwch
    -0.68
    Tembelea
    -0.67
     مشين
    -0.63
    MLLoader
    -0.60
    POSITIVE LOGITS
    makedirs
    0.43
     CoreData
    0.41
    PyExc
    0.40
    ruitment
    0.39
    PANY
    0.39
     ✭✭
    0.39
     chaus
    0.39
     activists
    0.39
    ädchen
    0.39
     féd
    0.39
    Activations Density 0.693%

    No Known Activations