© 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. 14680
    Prev
    Next
    INDEX
    Explanations

    information about events or series of publications, possibly including identifying information like dates and volume numbers

    oai_token-act-pair · gemini-2.0-flash

    series

    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
     series
    -3.47
    series
    -3.27
     Series
    -3.11
    Series
    -3.05
     SERIES
    -2.97
     serie
    -2.64
     série
    -2.64
    SERIES
    -2.59
    serie
    -2.22
     séries
    -2.19
    POSITIVE LOGITS
    XmlAccessType
    0.61
     kaynağından
    0.54
    ScopeManager
    0.53
     Wikime
    0.50
    WaitGroup
    0.49
    EndContext
    0.47
    ΡΑ
    0.46
     useRouter
    0.45
     Stande
    0.44
    migrationBuilder
    0.44
    Activations Density 2.835%

    No Known Activations