© 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. 113332
    Prev
    Next
    INDEX
    Explanations

    ah followed by various words

    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
    م
    1.69
    y
    1.54
    i
    1.48
    ي
    1.41
    é
    1.38
    ut
    1.29
     It
    1.28
    ம்
    1.21
    j
    1.19
    ം
    1.19
    POSITIVE LOGITS
    2
    1.39
    5
    1.30
    0
    1.27
    3
    1.21
    9
    1.19
    6
    1.16
    4
    1.11
    7
    1.07
    ized
    1.05
    ’
    1.00
    Activations Density 0.000%

    No Known Activations