© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    numerical citations and code snippets

    oai_token-act-pair · gemini-2.0-flash

    academic/legal citations

    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
     للاسماء
    -0.73
    featureID
    -0.70
    ValueStyle
    -0.69
    queryInterface
    -0.63
     Meksiku
    -0.63
    AddTagHelper
    -0.63
    httphttps
    -0.62
    ViewFeatures
    -0.62
    providedIn
    -0.61
    RetentionPolicy
    -0.61
    POSITIVE LOGITS
     leſs
    0.54
     minimo
    0.50
     incomplète
    0.49
     Etr
    0.49
    клопе
    0.48
     Monfieur
    0.47
    neſs
    0.47
     Lugo
    0.46
    InSection
    0.46
     Dore
    0.46
    Activations Density 7.885%

    No Known Activations