© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90333
    Prev
    Next
    INDEX
    Explanations

    darkly comedic

    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_23_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
    MAGIC
    0.37
    врат
    0.37
    ਦਾ
    0.36
     所有
    0.35
    㳒
    0.35
    ^{+}\
    0.34
    ими
    0.34
    ക്‌
    0.34
    囫
    0.34
    バイス
    0.33
    POSITIVE LOGITS
     Along
    0.33
    inderella
    0.31
    諒
    0.31
     duration
    0.30
     roaring
    0.30
    tgt
    0.30
    tten
    0.29
    Along
    0.29
    itake
    0.29
    مش
    0.29
    Activations Density 0.008%

    No Known Activations