© 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. 9765
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to conditional logic (`if`, `else`) and variable assignment/comparison (e.g., `:=`, `=`, `_`)

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     تضيفلها
    -0.66
    UnsafeEnabled
    -0.60
    ineno
    -0.59
     ModelExpression
    -0.58
    ⓧ
    -0.56
    Vidite
    -0.54
    msgTypes
    -0.53
     Dernière
    -0.52
    Personensuche
    -0.52
    
    -0.52
    POSITIVE LOGITS
    Naissance
    0.49
     leider
    0.48
     Bark
    0.45
    '])->
    0.45
    calipsis
    0.45
     Honorable
    0.45
    CodedInputStream
    0.44
    diğinde
    0.44
    ‍♀️
    0.44
    География
    0.43
    Activations Density 1.922%

    No Known Activations