© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134393
    Prev
    Next
    INDEX
    Explanations

    horsemanship

    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_1_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
    ти
    1.46
    ，
    1.03
    ،
    1.03
    soever
    0.98
    ↵↵
    0.91
     ولكن
    0.81
    と思います
    0.80
     lorsque
    0.80
    alysis
    0.77
    عة
    0.77
    POSITIVE LOGITS
     for
    1.45
    지
    1.33
    z
    1.18
    in
    1.13
    น
    1.13
    f
    1.10
    ن
    1.10
     with
    1.09
    AD
    1.06
     U
    1.04
    Activations Density 0.000%

    No Known Activations