© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6972
    Prev
    Next
    INDEX
    Explanations

    the phrase "full-time"

    oai_token-act-pair · gemini-2.0-flash

    full time positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     full
    -3.02
    Full
    -2.72
     Full
    -2.67
    full
    -2.67
     FULL
    -2.34
    FULL
    -2.33
     peł
    -1.64
     vollen
    -1.63
    フル
    -1.63
     pleine
    -1.60
    POSITIVE LOGITS
    jmp
    0.51
    sat
    0.49
    estanden
    0.48
    endmodule
    0.48
    EDEFAULT
    0.48
     חיצוניים
    0.47
    ship
    0.46
    VersionUID
    0.46
    getResultList
    0.45
    LookAnd
    0.44
    Activations Density 2.348%

    No Known Activations