© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14411
    Prev
    Next
    INDEX
    Explanations

    angle brackets, underscores, struct and define keywords, suggesting it identifies code snippets

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Tembelea
    -0.89
    رشف
    -0.88
     Савезне
    -0.83
     referenties
    -0.71
    amını
    -0.69
    rungsseite
    -0.65
    tagHelperRunner
    -0.65
     nahilalakip
    -0.65
     سكانية
    -0.63
     समीक्षाओं
    -0.63
    POSITIVE LOGITS
    andro
    0.44
    rail
    0.44
     example
    0.42
    ifter
    0.41
    ัส
    0.40
    laceae
    0.40
    skon
    0.40
     fairer
    0.40
     Past
    0.40
     FOOT
    0.39
    Activations Density 2.103%

    No Known Activations