© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5418
    Prev
    Next
    INDEX
    Explanations

    code snippets that use curly braces, parentheses, arrays, and semicolons

    oai_token-act-pair · gemini-2.0-flash

    parenthesis and braces

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    .
    -1.18
    ).
    -0.94
    ".
    -0.82
     .
    -0.79
     L
    -0.78
     (
    -0.78
     S
    -0.77
    !
    -0.76
     G
    -0.75
     C
    -0.75
    POSITIVE LOGITS
     Monfieur
    1.53
     myſelf
    1.48
     Theſe
    1.48
     Efq
    1.45
     itſelf
    1.45
     Мексичка
    1.31
     Majefty
    1.23
     doubtnut
    1.23
     мәкал
    1.23
    mybatisplus
    1.22
    Activations Density 0.911%

    No Known Activations