© 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. 15043
    Prev
    Next
    INDEX
    Explanations

    code snippets containing the keyword `public`.

    oai_token-act-pair · gemini-2.0-flash

    say static

    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
     dynamic
    -2.94
     Dynamic
    -2.75
    dynamic
    -2.69
    Dynamic
    -2.66
     static
    -2.56
     Static
    -2.55
     dynamically
    -2.53
     DYNAMIC
    -2.42
    Static
    -2.38
     dynamique
    -2.34
    POSITIVE LOGITS
     RoutedEventArgs
    0.47
    Contributors
    0.46
    Feature
    0.45
    PositiveButton
    0.44
     []:
    0.43
    essex
    0.43
    atru
    0.42
    hancers
    0.42
     Erişim
    0.42
    Armando
    0.42
    Activations Density 2.955%

    No Known Activations