© 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. 43789
    Prev
    Next
    INDEX
    Explanations

    Bandra, Bandiera, Bandar, BandLab

    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
    ب
    0.84
    ב
    0.79
    к
    0.70
    ры
    0.67
    ับ
    0.65
    soever
    0.63
    ปี
    0.63
    k
    0.62
    ська
    0.62
    st
    0.61
    POSITIVE LOGITS
    and
    0.64
     வெப்சீரி
    0.62
    ﺤ
    0.59
    ンダー
    0.58
    ﺘ
    0.56
     unchanged
    0.55
    WILLIAM
    0.55
     déterminé
    0.55
    rowning
    0.54
     alarmed
    0.54
    Activations Density 0.000%

    No Known Activations