© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13624
    Prev
    Next
    INDEX
    Explanations

    dates, timespans, and the start of processes around them

    oai_token-act-pair · gemini-2.0-flash

    specific programming or technical terms

    np_token-act-pair-logits · gpt-4o-mini

    starting dates/times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     gyhoeddwyd
    -0.56
     Вікіпе
    -0.49
    нъ
    -0.49
    RTLR
    -0.44
     lej
    -0.43
     بذ
    -0.42
     rots
    -0.41
    anglès
    -0.41
    createFrom
    -0.40
     ModelExpression
    -0.40
    POSITIVE LOGITS
     виправивши
    0.63
     مرئيه
    0.63
     createContext
    0.62
     StatelessWidget
    0.61
    cembre
    0.60
    WEDNESDAY
    0.60
    InjectAttribute
    0.59
    GeneratedValue
    0.59
    IntoConstraints
    0.59
     Sept
    0.59
    Activations Density 1.810%

    No Known Activations