© 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. 8720
    Prev
    Next
    INDEX
    Explanations

    source code with numbers, symbols and specific naming conventions

    oai_token-act-pair · gemini-2.0-flash

    code and math expressions

    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
    出版年
    -0.77
    makeText
    -0.59
    μφωνα
    -0.57
    ScopeManager
    -0.52
    MethodManager
    -0.52
     anges
    -0.52
    LikeLike
    -0.52
    awtextra
    -0.50
     consultato
    -0.50
    — 
    -0.50
    POSITIVE LOGITS
    QMetaType
    0.65
    printStackTrace
    0.64
    elemField
    0.62
     Biôgrafia
    0.56
    mybatisplus
    0.55
    хьтан
    0.54
    jws
    0.53
     HttpHeaders
    0.52
     Italijani
    0.52
     незавершена
    0.52
    Activations Density 2.750%

    No Known Activations