© 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. 12141
    Prev
    Next
    INDEX
    Explanations

    references to personal information, affiliations, and locations.

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     useParams
    -0.54
    ArgsConstructor
    -0.52
     CreateTagHelper
    -0.52
    ┛
    -0.52
    ThroughAttribute
    -0.52
    談社
    -0.50
     poveznice
    -0.50
     établi
    -0.49
    εια
    -0.48
     فريبيس
    -0.47
    POSITIVE LOGITS
     kaarangay
    0.57
    transQ
    0.54
     graduate
    0.52
    graduate
    0.51
    fromnode
    0.48
    vius
    0.48
     phosphat
    0.47
     typelib
    0.47
    プーン
    0.47
     GenerationType
    0.46
    Activations Density 1.668%

    No Known Activations