© 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. 195248
    Prev
    Next
    INDEX
    Explanations

    im

    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
    ঙ্কার
    0.44
     बढ़ाते
    0.42
    全然
    0.38
    wear
    0.37
     কর্মীদের
    0.37
     நடத்து
    0.37
     正規
    0.37
     कई
    0.36
    完全
    0.36
    靼
    0.36
    POSITIVE LOGITS
     am
    0.58
    Am
    0.44
     Am
    0.42
     ام
    0.41
    Bias
    0.40
    Im
    0.39
     أم
    0.38
    Bien
    0.38
     heading
    0.38
    Refer
    0.38
    Activations Density 0.002%

    No Known Activations