© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2693
    Prev
    Next
    INDEX
    Explanations

    code syntax elements such as symbols, operators, or keywords from C-based languages

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords and syntax

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

    code 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
    Przypisy
    -0.69
     &
    -0.66
    KURZBESCHREIBUNG
    -0.63
     chi̍t
    -0.63
     &_
    -0.63
     turn
    -0.62
     Turn
    -0.62
    endpush
    -0.61
    ⋙
    -0.61
     simplifié
    -0.60
    POSITIVE LOGITS
     võimal
    0.49
    üstü
    0.48
    læg
    0.45
    ftagPool
    0.43
    Ret
    0.42
     AssemblyCulture
    0.42
    httphttps
    0.41
    tis
    0.41
    vereins
    0.41
    ChromeDriver
    0.39
    Activations Density 1.962%

    No Known Activations