© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11286
    Prev
    Next
    INDEX
    Explanations

    single digit numbers or pairs of numbers separated by a period or hyphen

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or programming-related terms

    np_token-act-pair-logits · gpt-4o-mini

    code and technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     الحره
    -0.89
    BufferException
    -0.69
    AddTagHelper
    -0.68
    <*
    -0.67
    kuuta
    -0.66
    writeFieldEnd
    -0.65
    StoryboardSegue
    -0.63
     كومونز
    -0.60
    DoubleQuotes
    -0.60
     للاسماء
    -0.59
    POSITIVE LOGITS
     parabolic
    0.57
     convective
    0.52
     StringTokenizer
    0.50
    حياتها
    0.50
    fatalError
    0.49
    lections
    0.48
     doute
    0.48
     contrário
    0.47
    inars
    0.47
    InitVars
    0.47
    Activations Density 8.664%

    No Known Activations