© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88671
    Prev
    Next
    INDEX
    Explanations

    staple food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    m
    0.82
     incend
    0.74
    mış
    0.72
    রে
    0.69
    ס
    0.67
    வ
    0.66
    mallow
    0.66
     ות
    0.66
    )
    0.64
     distint
    0.63
    POSITIVE LOGITS
    t
    0.91
    ან
    0.76
    <0xE8>
    0.65
    ус
    0.63
    asing
    0.63
    З
    0.61
    ans
    0.60
    is
    0.59
    ляются
    0.57
    ри
    0.57
    Activations Density 0.000%

    No Known Activations