© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1958
    Prev
    Next
    INDEX
    Explanations

    mentions of problems, questions about how to fix something, and requests for help.

    oai_token-act-pair · gemini-2.0-flash

    help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Pries
    -0.52
    fillType
    -0.49
    RUnlock
    -0.47
     vaut
    -0.47
     espagnole
    -0.46
    HandlerContext
    -0.46
    chants
    -0.46
     flocc
    -0.46
     Collar
    -0.45
     Esprit
    -0.45
    POSITIVE LOGITS
     help
    2.50
    help
    2.38
     assistance
    2.25
     Help
    2.19
    Help
    2.17
     assist
    2.11
     HELP
    2.09
    HELP
    2.05
    assistance
    1.99
     aid
    1.96
    Activations Density 1.856%

    No Known Activations