© 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. 104044
    Prev
    Next
    INDEX
    Explanations

    interrogative forms

    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
    c
    2.19
    y
    1.91
    p
    1.90
    t
    1.83
    you
    1.77
    v
    1.76
    f
    1.73
    k
    1.71
    g
    1.70
    is
    1.66
    POSITIVE LOGITS
    ни
    1.37
    ία
    1.22
    ని
    1.04
    進
    1.02
    ۳
    1.01
    ৩
    1.00
    ップ
    0.98
    К
    0.97
    两
    0.95
    几
    0.95
    Activations Density 0.000%

    No Known Activations