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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3177
    Prev
    Next
    INDEX
    Explanations

    angular, react, or nestjs

    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_5_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
    n
    0.97
    ان
    0.84
    ه
    0.80
    etable
    0.77
    [[
    0.74
    skraft
    0.68
    ла
    0.68
    ют
    0.67
    로
    0.66
    н
    0.66
    POSITIVE LOGITS
    ی
    0.74
     laborales
    0.72
    fis
    0.71
    riva
    0.68
    tae
    0.67
    Scaler
    0.67
    beeld
    0.66
    FolderName
    0.66
    Prosecutors
    0.66
     겨
    0.66
    Activations Density 0.002%

    No Known Activations