© 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. 113328
    Prev
    Next
    INDEX
    Explanations

    multilingual components

    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
    ة
    1.38
    ли
    1.34
    ни
    1.33
    ко
    1.21
    т
    1.17
    ૦
    1.17
    ing
    1.13
    IS
    1.10
    <0x80>
    1.09
    IN
    1.02
    POSITIVE LOGITS
     is
    1.40
    ↵
    1.17
    op
    0.98
    iel
    0.83
    agem
    0.80
    heten
    0.79
    issä
    0.79
    ökk
    0.79
    uti
    0.78
    osan
    0.78
    Activations Density 0.000%

    No Known Activations