© 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. 10134
    Prev
    Next
    INDEX
    Explanations

    mentions of roads, leaks, wetness and bodily functions.

    oai_token-act-pair · gemini-2.0-flash

    water/wetness

    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
    MigrationBuilder
    -0.82
     विश्वसनीयता
    -0.82
    DispatchToProps
    -0.78
    ArgsConstructor
    -0.77
     بيها
    -0.74
     ویکی‌پدی
    -0.73
    ToProps
    -0.73
    URLException
    -0.72
     contextLoads
    -0.72
     CreateTagHelper
    -0.70
    POSITIVE LOGITS
     d
    0.79
     g
    0.59
     soak
    0.52
     sog
    0.50
     mo
    0.49
     dou
    0.45
     pooling
    0.44
     trick
    0.43
     Bat
    0.43
    ake
    0.42
    Activations Density 1.740%

    No Known Activations