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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6755
    Prev
    Next
    INDEX
    Explanations

    words that describe the quality, amount, or size of something

    oai_token-act-pair · gemini-2.0-flash

    support

    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
    QMetaType
    -0.95
    WebElementEntity
    -0.81
     disambiguazione
    -0.79
    UrlResolution
    -0.79
    ptonshire
    -0.75
    évaluateur
    -0.73
    verwijspagina
    -0.73
     considerable
    -0.70
    vellous
    -0.68
     enormous
    -0.68
    POSITIVE LOGITS
     viață
    0.56
     indietro
    0.54
     Référence
    0.50
     pousse
    0.48
    superuser
    0.48
     oreille
    0.48
     étag
    0.48
     certamen
    0.47
     kropp
    0.47
     ře
    0.47
    Activations Density 1.453%

    No Known Activations