© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82076
    Prev
    Next
    INDEX
    Explanations

    acceptance of imperfections

    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_29_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
    唵
    0.42
     lak
    0.41
     tir
    0.38
     ২টি
    0.37
     πριν
    0.37
     sphinx
    0.37
     prized
    0.36
     Astros
    0.36
    vcx
    0.36
    𒀊
    0.36
    POSITIVE LOGITS
     uncertainty
    0.38
     juga
    0.37
    搭配
    0.37
    кож
    0.37
    向上
    0.36
    !
    0.36
    дать
    0.36
     ঝুঁক
    0.36
    மையும்
    0.35
     вообще
    0.35
    Activations Density 0.006%

    No Known Activations