© 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. 203700
    Prev
    Next
    INDEX
    Explanations

    amount

    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
    al
    1.44
    ad
    1.22
    1.18
    u
    1.14
    o
    1.09
    -
    1.08
    ing
    1.06
    ik
    1.05
    in
    1.00
    ल
    1.00
    POSITIVE LOGITS
     Когда
    1.17
     Б
    1.04
     Х
    1.02
     Можно
    1.01
     Что
    0.95
     Зна
    0.93
    ри
    0.93
     Л
    0.93
     Χ
    0.92
     Ж
    0.91
    Activations Density 0.002%

    No Known Activations