© 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. 62957
    Prev
    Next
    INDEX
    Explanations

    forbidden actions

    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
     estudo
    0.40
     []);
    0.38
    apart
    0.37
     longiore
    0.37
     महीना
    0.37
    嵌
    0.37
     இலங்க
    0.36
     Antennes
    0.36
    中は
    0.36
     apart
    0.36
    POSITIVE LOGITS
     ser
    0.44
     Ser
    0.40
     denial
    0.40
    නා
    0.40
    сылка
    0.40
    Ser
    0.39
     spect
    0.39
     سر
    0.38
     initiated
    0.38
     ઘ
    0.38
    Activations Density 0.000%

    No Known Activations