© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162146
    Prev
    Next
    INDEX
    Explanations

    skankhunt

    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_2_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
    ۹
    1.16
    atud
    1.07
    ్రో
    0.96
    ۳
    0.95
    锵
    0.95
     энерги
    0.91
     Олег
    0.90
     batted
    0.89
    ције
    0.89
     bằng
    0.89
    POSITIVE LOGITS
    an
    1.63
    ing
    1.53
    um
    1.50
     on
    1.49
    on
    1.46
    ang
    1.44
    ने
    1.43
    ung
    1.35
    ü
    1.35
    ع
    1.28
    Activations Density 0.000%

    No Known Activations