© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31451
    Prev
    Next
    INDEX
    Explanations

    sub supra supersonic

    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_7_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
    i
    1.27
    e
    1.23
    s
    1.17
    et
    1.06
    a
    1.03
    b
    1.02
    y
    1.01
    c
    0.98
    om
    0.98
    this
    0.97
    POSITIVE LOGITS
    า
    1.05
    я
    1.00
    ة
    0.95
     ಸ್ಟ
    0.93
    り
    0.91
    입니다
    0.89
    用い
    0.89
    し
    0.88
    ী
    0.87
     дві
    0.86
    Activations Density 0.000%

    No Known Activations