© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260311
    Prev
    Next
    INDEX
    Explanations

    time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    echolog
    0.59
    SupportPackage
    0.59
    hiyam
    0.58
    ént
    0.55
    Ⲁ
    0.54
    ėtų
    0.53
    UISelectors
    0.53
     Suh
    0.52
     Suga
    0.52
    izma
    0.51
    POSITIVE LOGITS
    >
    0.51
    |
    0.45
     will
    0.43
    5
    0.43
    ',
    0.43
    ↵
    0.42
    \
    0.42
    ไม่
    0.41
    '
    0.41
     परे
    0.41
    Activations Density 0.002%

    No Known Activations