© 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. 12894
    Prev
    Next
    INDEX
    Explanations

    words used as identifiers in computer code, especially those related to users, branches, roles, and languages

    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_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
    StoryboardSegue
    -0.91
    +#+#
    -0.86
     ExecuteAsync
    -0.73
    setVerticalGroup
    -0.73
    ंदीखरीदारी
    -0.71
    rawDesc
    -0.69
    IBarButtonItem
    -0.66
    PMailer
    -0.65
     Administrativna
    -0.64
     تانيه
    -0.63
    POSITIVE LOGITS
     e
    0.48
    bootstrapcdn
    0.46
     where
    0.43
     csal
    0.43
    odend
    0.42
     i
    0.41
    gridx
    0.41
     fan
    0.40
    ņem
    0.40
     ettiği
    0.39
    Activations Density 2.619%

    No Known Activations