© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203601
    Prev
    Next
    INDEX
    Explanations

    fluffing rice with a fork

    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_6_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
    ق
    1.39
     latérales
    1.14
    ج
    1.14
     obstáculos
    1.12
    การ
    1.03
     extensión
    1.03
    کم
    1.01
    ް
    1.01
    ک
    1.00
    ك
    1.00
    POSITIVE LOGITS
    an
    1.25
    n
    1.03
    r
    0.96
    i
    0.94
    ana
    0.91
    that
    0.90
    iat
    0.87
    ra
    0.86
    a
    0.85
    ern
    0.85
    Activations Density 0.000%

    No Known Activations