© 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. 103758
    Prev
    Next
    INDEX
    Explanations

    foreign script characters

    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
    А
    1.21
    ו
    1.19
     pudi
    1.18
    정
    1.14
    ing
    1.13
    상
    1.13
     effectu
    1.12
    መም
    1.10
    The
    1.09
    મ
    1.09
    POSITIVE LOGITS
    s
    1.58
    de
    1.40
    ↵
    1.39
     to
    1.02
    dan
    0.97
    ter
    0.97
     you
    0.96
     demonstrated
    0.95
    mente
    0.94
     minimalist
    0.94
    Activations Density 0.000%

    No Known Activations