© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35211
    Prev
    Next
    INDEX
    Explanations

    material types and uses

    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_11_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
    ING
    0.73
    ION
    0.62
     cần
    0.61
    рень
    0.57
    ке
    0.55
     أغ
    0.54
    КУ
    0.54
    >`;
    0.54
     compels
    0.54
    एफ
    0.53
    POSITIVE LOGITS
    é
    0.87
    a
    0.66
    éz
    0.63
    de
    0.59
    DOMContentLoaded
    0.58
    Seit
    0.58
    meler
    0.57
    ুল
    0.56
    เมื่อ
    0.55
    ibid
    0.55
    Activations Density 0.008%

    No Known Activations