© 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. 12410
    Prev
    Next
    INDEX
    Explanations

    technical writing describing process and functionality.

    oai_token-act-pair · gemini-2.0-flash

    way such

    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
     ©️
    -0.72
    DoubleQuotes
    -0.59
     vuitton
    -0.59
    jsonwebtoken
    -0.59
    <bos>
    -0.57
     <<<<<<<<<<<<<<
    -0.55
    InSection
    -0.54
    mercury
    -0.54
    /*
    -0.50
     gibber
    -0.50
    POSITIVE LOGITS
     يتيمه
    0.62
    parsedMessage
    0.58
     przecież
    0.56
    ();)
    0.56
    verwijspagina
    0.54
    ConstraintMaker
    0.52
    addCriterion
    0.52
    design
    0.50
    EXISTS
    0.50
    Einzelnachweise
    0.48
    Activations Density 2.042%

    No Known Activations