© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107061
    Prev
    Next
    INDEX
    Explanations

    arduino code, sketches, commands

    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_2_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
    0
    1.71
    '
    1.63
    ’
    1.37
    H
    1.22
    M
    1.21
    ‘
    1.19
    j
    1.18
    with
    1.17
    Α
    1.13
    П
    1.07
    POSITIVE LOGITS
    ها
    1.33
    ية
    1.30
    يل
    1.28
    ى
    1.27
    ين
    1.13
    ре
    1.11
    та
    1.11
    ري
    1.11
    да
    1.09
    ુ
    1.06
    Activations Density 0.001%

    No Known Activations