© 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. 10717
    Prev
    Next
    INDEX
    Explanations

    code snippets and XML tags and attributes

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    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
    nsf
    -0.48
    rosh
    -0.46
     fråga
    -0.46
    subset
    -0.45
    ":"",
    -0.44
    Vidite
    -0.44
     autoridad
    -0.43
    rrggbb
    -0.43
    AutoField
    -0.43
     tokenId
    -0.42
    POSITIVE LOGITS
     للمعارف
    0.73
    RenderAtEndOf
    0.71
    URLException
    0.65
    GeneratedCode
    0.65
     AspNetCore
    0.63
     nahilalakip
    0.62
    WindowListener
    0.62
     Normdatei
    0.61
    PerformLayout
    0.60
     Jefus
    0.60
    Activations Density 3.955%

    No Known Activations