© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4109
    Prev
    Next
    INDEX
    Explanations

    text related to high school sports

    oai_token-act-pair · gemini-2.0-flash

    metadata

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ویکی‌پدیای
    -0.52
    bonucle
    -0.45
    ');?>
    -0.45
    '/>
    -0.45
     fav
    -0.43
    ochet
    -0.42
     endblock
    -0.42
    koda
    -0.41
    beiro
    -0.40
     disse
    -0.40
    POSITIVE LOGITS
    Personensuche
    0.69
    featureID
    0.68
    addCriterion
    0.68
     defStyleAttr
    0.66
    aarrggbb
    0.63
     متعلقه
    0.61
    ########.
    0.60
    MLLoader
    0.59
    Sitemap
    0.59
    WireFormatLite
    0.58
    Activations Density 1.046%

    No Known Activations