© 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. 2393
    Prev
    Next
    INDEX
    Explanations

    text related to book reviews, awards, and authors

    oai_token-act-pair · gemini-2.0-flash

    Writing and publishing context

    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
    Cyfeiriadau
    -0.62
     myö
    -0.56
    CrossRef
    -0.47
    tikzpicture
    -0.47
    ministrazione
    -0.46
    visející
    -0.46
    cloudflare
    -0.45
    Ци
    -0.45
    UPI
    -0.45
    abestanden
    -0.45
    POSITIVE LOGITS
     humaine
    0.63
    CodedInputStream
    0.62
    aronder
    0.59
     Partagez
    0.56
    phins
    0.54
    NewUrlParser
    0.54
     JsonResult
    0.53
    RegistryLite
    0.52
     Voir
    0.52
    >';
    0.52
    Activations Density 1.322%

    No Known Activations