© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10706
    Prev
    Next
    INDEX
    Explanations

    contract clauses protecting a company from liability.

    oai_token-act-pair · gemini-2.0-flash

    legal liability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    XmlAccessorType
    -0.73
    MemoryWarning
    -0.69
     виправивши
    -0.63
    rawDesc
    -0.59
    GeneratedValue
    -0.58
    SourceChecksum
    -0.57
    WebElementEntity
    -0.56
    documentclass
    -0.56
     continúas
    -0.52
    ScopeManager
    -0.52
    POSITIVE LOGITS
     damage
    0.57
    참고
    0.53
     дописавши
    0.53
    damage
    0.51
     loss
    0.50
    jenih
    0.50
    ızlık
    0.49
    ďaka
    0.47
    IPAC
    0.47
    culously
    0.47
    Activations Density 1.281%

    No Known Activations