© 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. 3249
    Prev
    Next
    INDEX
    Explanations

    words relating to representation, reflection, and demonstration.

    oai_token-act-pair · gemini-2.0-flash

    ways of expression

    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
    Datuak
    -0.60
     flyknit
    -0.50
     magnétique
    -0.44
     onResponse
    -0.43
     eorum
    -0.43
     volando
    -0.42
     Comentarios
    -0.42
    ViewImports
    -0.42
     inalámb
    -0.41
     laiton
    -0.41
    POSITIVE LOGITS
     how
    0.78
     the
    0.73
     what
    0.68
    <bos>
    0.64
     EconPapers
    0.62
     @"/
    0.60
    rans
    0.57
    Jeografia
    0.56
     a
    0.56
    parsedMessage
    0.55
    Activations Density 4.764%

    No Known Activations