© 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. 6981
    Prev
    Next
    INDEX
    Explanations

    code-related keywords like symbols, font, and bool

    oai_token-act-pair · gemini-2.0-flash

    Icons and Symbols

    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
     symbols
    -2.50
     symbol
    -2.45
     Symbols
    -2.30
     Symbol
    -2.27
     SYMBOL
    -2.19
     icon
    -2.14
     symbolic
    -2.14
     icons
    -2.11
    symbol
    -2.09
     Icon
    -2.09
    POSITIVE LOGITS
    ніципалі
    0.60
    findpost
    0.56
     rhestr
    0.54
    WriteTagHelper
    0.52
    참고
    0.49
    UIControlState
    0.47
    inerja
    0.47
    essoal
    0.46
     Morty
    0.46
    ATEUR
    0.46
    Activations Density 1.674%

    No Known Activations