© 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. 5607
    Prev
    Next
    INDEX
    Explanations

    various non-alphabetic characters, file sizes, and line numbers

    oai_token-act-pair · gemini-2.0-flash

    diverse file formats or programming constructs

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

    single digit numbers

    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
    Page
    -0.62
     oprot
    -0.56
    migrationBuilder
    -0.56
     fondateur
    -0.55
     artificiales
    -0.53
     tramonto
    -0.52
     sidan
    -0.52
     Page
    -0.51
    page
    -0.50
    itaal
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.69
    ثيق
    0.58
     Drapeau
    0.57
    EndInit
    0.52
     lenker
    0.51
    WithFormat
    0.50
    ecé
    0.50
    참고
    0.49
    ΗΣ
    0.48
    といけない
    0.47
    Activations Density 5.134%

    No Known Activations