© 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. 229596
    Prev
    Next
    INDEX
    Explanations

    Mewtwo Bentō Dragonite

    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
    -
    1.06
    ना
    0.77
     나누
    0.76
    ﺔ
    0.76
     penchant
    0.76
     splendor
    0.75
     overboard
    0.75
    nę
    0.73
    ExtensionsPath
    0.73
    rs
    0.72
    POSITIVE LOGITS
    on
    1.27
    ف
    1.24
    X
    1.03
    지
    1.01
    iv
    1.00
    C
    0.98
    B
    0.98
    W
    0.98
    in
    0.93
    ý
    0.91
    Activations Density 0.000%

    No Known Activations