© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 513
    Prev
    Next
    INDEX
    Explanations

    the keyword "void" within a code snippet

    oai_token-act-pair · gemini-2.0-flash

    say "set"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SourceChecksum
    -0.88
     Roskov
    -0.88
    featureID
    -0.79
    Vidite
    -0.78
     الدولى
    -0.78
     kasarigan
    -0.77
     وتسجيلات
    -0.76
    RegressionTest
    -0.76
    Халык
    -0.73
     étranger
    -0.71
    POSITIVE LOGITS
    1
    0.35
    2
    0.35
    .,
    0.34
    ArgsConstructor
    0.34
    ），
    0.32
    /,
    0.31
    7
    0.31
    )，
    0.30
     ，
    0.29
    3
    0.29
    Activations Density 0.155%

    No Known Activations