© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135266
    Prev
    Next
    INDEX
    Explanations

    travel and books

    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_1_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
    on
    1.51
    c
    1.41
    as
    1.37
    v
    1.26
    of
    1.17
    3
    1.16
    re
    1.15
    os
    1.12
    an
    1.11
    ش
    1.11
    POSITIVE LOGITS
    ۰
    0.90
    ០
    0.89
    ]，
    0.78
    நபியே
    0.77
    ０
    0.76
    desIP
    0.75
    0
    0.75
    ও
    0.68
    ﻓ
    0.68
    desPort
    0.67
    Activations Density 0.005%

    No Known Activations