© 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. 62862
    Prev
    Next
    INDEX
    Explanations

    eye of the beholder

    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
    Negative Logits
    f
    1.39
    quela
    1.27
    rest
    1.18
    ні
    1.17
    xlsx
    1.15
    zigzag
    1.14
    quele
    1.13
    fahrer
    1.09
    skih
    1.07
    fot
    1.06
    POSITIVE LOGITS
     for
    1.86
     with
    1.54
     has
    1.49
    '
    1.48
     from
    1.45
     by
    1.43
     was
    1.36
     no
    1.34
     The
    1.34
    IS
    1.34
    Activations Density 0.000%

    No Known Activations