© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202091
    Prev
    Next
    INDEX
    Explanations

    cloud provider

    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
    ।
    0.95
    。
    0.89
    يا
    0.75
    ،
    0.73
    ，
    0.72
    ز
    0.70
    ו
    0.68
    ។
    0.65
    ۔
    0.61
    s
    0.59
    POSITIVE LOGITS
    𝘢
    0.66
    alakip
    0.64
    a
    0.61
     всі
    0.60
     Adresse
    0.60
     Banyak
    0.60
    Ƒ
    0.56
     as
    0.55
     Cliquez
    0.55
    शुदा
    0.55
    Activations Density 0.002%

    No Known Activations