© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60175
    Prev
    Next
    INDEX
    Explanations

    month, year, or apprentice

    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
    s
    1.44
    k
    1.06
    ের
    1.04
    ’
    1.02
    kval
    1.01
    ्स
    0.99
    That
    0.98
    ों
    0.97
    iy
    0.93
    ים
    0.93
    POSITIVE LOGITS
    습니다
    1.03
    ة
    0.98
    ，
    0.98
    し
    0.98
    an
    0.97
    it
    0.94
    ；
    0.93
    ;
    0.93
    ется
    0.91
    нения
    0.87
    Activations Density 0.004%

    No Known Activations