© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12827
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are part of a discussion such as 'I', 'm','the', time, get

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    abestanden
    -0.74
    windowFixed
    -0.73
     beginnetje
    -0.73
     дописавши
    -0.73
     supposed
    -0.69
    expandindo
    -0.68
    +#+#
    -0.68
    Pautan
    -0.66
    supposed
    -0.63
    MigrationBuilder
    -0.63
    POSITIVE LOGITS
     riduzione
    0.49
     partenza
    0.49
    tences
    0.48
     rodada
    0.44
    ánico
    0.43
    honneur
    0.43
     tartalmaz
    0.42
    >";
    0.41
    வும்
    0.40
     רב
    0.40
    Activations Density 10.447%

    No Known Activations