© 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. 103254
    Prev
    Next
    INDEX
    Explanations

    Surnames: Williams, Kee, Harbor, Stone, Lewis, Griffiths, Lee

    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
     and
    1.14
    ש
    0.95
    r
    0.91
    大
    0.91
    おそらく
    0.89
    し
    0.89
    int
    0.85
    ाराम
    0.84
    おしゃれ
    0.84
    1
    0.84
    POSITIVE LOGITS
    ۔
    1.13
    ↵
    1.04
    ক
    1.02
     comforted
    0.96
    ЕМ
    0.95
    ли
    0.94
    ла
    0.93
    cuando
    0.93
    ﻏ
    0.92
     deben
    0.90
    Activations Density 0.000%

    No Known Activations