© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3185
    Prev
    Next
    INDEX
    Explanations

    words related to plot and story elements.

    oai_token-act-pair · gemini-2.0-flash

    described environments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -2.72
    full
    -2.67
    Full
    -2.63
     Full
    -2.58
    FULL
    -2.23
     FULL
    -2.09
     vollen
    -1.70
     penuh
    -1.67
     peł
    -1.61
     pleine
    -1.60
    POSITIVE LOGITS
    出版年
    0.82
    AndEndTag
    0.71
     للاسماء
    0.70
    IntoConstraints
    0.66
    Personensuche
    0.65
    GenerationType
    0.65
    thâu
    0.64
    OutputPath
    0.63
     oprot
    0.62
    softc
    0.61
    Activations Density 1.368%

    No Known Activations