© 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. 57672
    Prev
    Next
    INDEX
    Explanations

    gondola ride

    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
    <0x80>
    1.05
    م
    1.02
     pouze
    1.01
    ul
    0.98
     destac
    0.97
    ный
    0.96
    os
    0.95
    ની
    0.95
    ين
    0.94
    as
    0.91
    POSITIVE LOGITS
     I
    1.59
     are
    1.49
     at
    1.34
    ل
    1.31
    ।
    1.26
     a
    1.24
     to
    1.24
    ll
    1.20
    ک
    1.16
     (
    1.16
    Activations Density 0.000%

    No Known Activations