© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12291
    Prev
    Next
    INDEX
    Explanations

    PHP code syntax, specifically associated with object properties, return types, and class definitions

    oai_token-act-pair · gemini-2.0-flash

    newline characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.63
     通販
    -0.56
     debout
    -0.51
    genden
    -0.51
    ヮ
    -0.51
    ukunft
    -0.50
    väg
    -0.48
     względu
    -0.48
     kapcsolat
    -0.48
     volna
    -0.47
    POSITIVE LOGITS
    awtextra
    0.77
    oredCriteria
    0.67
    DockStyle
    0.60
    jer
    0.53
    middels
    0.53
    expandindo
    0.52
     '\\;'
    0.52
    execSQL
    0.52
    CloseOperation
    0.50
     AssemblyTitle
    0.47
    Activations Density 0.475%

    No Known Activations