© 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. 6874
    Prev
    Next
    INDEX
    Explanations

    mentions of "fair game" and related legal arguments.

    oai_token-act-pair · gemini-2.0-flash

    fair

    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
     fair
    -3.45
     Fair
    -3.14
    Fair
    -3.11
    fair
    -2.92
     FAIR
    -2.81
    FAIR
    -2.64
     fairness
    -2.23
     fairer
    -2.19
     fairest
    -2.11
     fairs
    -2.06
    POSITIVE LOGITS
    enumi
    0.57
    ArgsConstructor
    0.54
    UnknownFieldSet
    0.51
    uchungen
    0.50
    __*/
    0.49
    msgTypes
    0.48
    edly
    0.47
     theſe
    0.46
    expandindo
    0.46
    gráfica
    0.45
    Activations Density 3.858%

    No Known Activations