© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11429
    Prev
    Next
    INDEX
    Explanations

    the word "literature"

    oai_token-act-pair · gemini-2.0-flash

    literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    MigrationBuilder
    -1.09
     disambiguazione
    -1.09
    <bos>
    -1.08
    featureID
    -0.93
    الحياه
    -0.90
    migrationBuilder
    -0.88
     ***!
    -0.85
    rungsseite
    -0.84
    ⓧ
    -0.83
     AssemblyCulture
    -0.82
    POSITIVE LOGITS
    ://"
    0.62
    ffer
    0.60
    crow
    0.57
    ers
    0.54
    igo
    0.51
    lø
    0.51
     props
    0.50
    loway
    0.50
    tero
    0.50
    lo
    0.50
    Activations Density 1.081%

    No Known Activations