© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46385
    Prev
    Next
    INDEX
    Explanations

    drives

    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_10_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
    hi
    0.23
     ป
    0.21
    ﻯ
    0.20
    ↵↵
    0.20
     drives
    0.20
    hhh
    0.20
    kin
    0.19
    hh
    0.19
     logarithms
    0.19
    可能性がある
    0.19
    POSITIVE LOGITS
    ా
    0.35
    с
    0.34
    ات
    0.32
    т
    0.29
    다
    0.28
    но
    0.28
    스
    0.27
    да
    0.26
    ou
    0.26
    و
    0.26
    Activations Density 0.007%

    No Known Activations