© 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. 106867
    Prev
    Next
    INDEX
    Explanations

    information word endings

    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
    {
    1.33
    -
    1.23
    ES
    1.07
    CH
    1.06
    '
    1.05
    öy
    1.02
    EE
    1.01
    OS
    0.99
    DA
    0.98
    (
    0.98
    POSITIVE LOGITS
    д
    1.33
    ll
    1.27
    其他
    1.27
     on
    1.27
    t
    1.26
    و
    1.17
    ли
    1.16
    大
    1.16
    ن
    1.14
    tion
    1.08
    Activations Density 0.000%

    No Known Activations