© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137100
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    intensité
    0.43
     intensity
    0.42
     verification
    0.42
     Mitarbeit
    0.41
    ರೀಕ್ಷ
    0.41
    ']>
    0.39
     severity
    0.39
     Aless
    0.39
     scenario
    0.39
     WITH
    0.38
    POSITIVE LOGITS
     recurs
    0.48
     actu
    0.41
    上下
    0.41
    possibly
    0.40
    意见
    0.39
    AspNetUser
    0.38
    Quin
    0.38
    पूर्व
    0.38
    ியில்
    0.37
    籾
    0.37
    Activations Density 0.001%

    No Known Activations