© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15975
    Prev
    Next
    INDEX
    Explanations

    code syntax related to software services and controllers

    oai_token-act-pair · gemini-2.0-flash

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    paramref
    -0.59
    badlogic
    -0.50
    çais
    -0.47
     notice
    -0.44
    AddAttribute
    -0.44
    opener
    -0.42
     mense
    -0.42
    flood
    -0.41
    جل
    -0.40
    cerna
    -0.40
    POSITIVE LOGITS
    rungsseite
    0.69
    Personensuche
    0.66
    "]);
    0.62
    ⓧ
    0.60
     taches
    0.58
    ".
    0.58
     ModelExpression
    0.57
    AccessorTable
    0.56
    styleType
    0.56
    DoubleQuotes
    0.56
    Activations Density 0.116%

    No Known Activations