© 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. 89026
    Prev
    Next
    INDEX
    Explanations

    MX Red, Chick, cicchetti, Span

    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
    д
    0.86
    ш
    0.82
    ش
    0.74
    د
    0.73
    ñal
    0.70
    غير
    0.69
    ING
    0.68
    ب
    0.68
    ਸ਼
    0.67
    s
    0.67
    POSITIVE LOGITS
    ן
    0.74
    ない
    0.70
     multiplex
    0.61
    ור
    0.59
    ค
    0.57
    ου
    0.57
    <0x80>
    0.54
     başlat
    0.54
    ก
    0.53
     watershed
    0.52
    Activations Density 0.000%

    No Known Activations