© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76974
    Prev
    Next
    INDEX
    Explanations

    tank

    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_53_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
    ക്കാല
    0.45
    கார
    0.41
     Ấ
    0.40
     Tang
    0.38
    >,</
    0.37
    adays
    0.37
    肠
    0.36
     දී
    0.35
     Mus
    0.35
     Tid
    0.35
    POSITIVE LOGITS
    льным
    0.41
    uline
    0.41
    ளா
    0.40
    vf
    0.39
    L
    0.39
    uitar
    0.38
    льном
    0.38
    ُل
    0.38
    Lit
    0.37
    雳
    0.37
    Activations Density 0.001%

    No Known Activations