© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107741
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ud
    1.41
    ile
    1.22
     is
    1.20
    am
    1.15
     و
    1.14
    ä
    1.12
    in
    1.11
    em
    1.08
    al
    1.07
    um
    1.07
    POSITIVE LOGITS
    ي
    1.33
     peux
    1.13
    י
    1.10
    м
    1.09
    ﻱ
    1.07
     ouv
    1.05
     niedr
    1.03
     první
    1.02
     corne
    1.00
    خفض
    0.99
    Activations Density 0.000%

    No Known Activations