© 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. 4570
    Prev
    Next
    INDEX
    Explanations

    references to news articles and page numbers

    oai_token-act-pair · gemini-2.0-flash

    references, URLs, 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_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
     tartalomajánló
    -0.68
    reporter
    -0.63
    SequentialGroup
    -0.61
     straips
    -0.61
     articles
    -0.60
    selle
    -0.60
     Préférences
    -0.59
    ColumnHeaders
    -0.58
    EndGlobalSection
    -0.58
     reporter
    -0.58
    POSITIVE LOGITS
    GEBURTSDATUM
    0.57
    CloseOperation
    0.50
    numerusform
    0.47
    bilidad
    0.43
    httphttps
    0.43
    NullCheck
    0.42
    يكب
    0.41
     écran
    0.41
     perpétu
    0.41
     defaultstate
    0.41
    Activations Density 0.361%

    No Known Activations