© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8630
    Prev
    Next
    INDEX
    Explanations

    victim / victims

    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_13_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
    윽
    0.45
    ров
    0.44
    mean
    0.40
    proba
    0.39
    늡
    0.38
     to
    0.38
    ރު
    0.38
    л
    0.37
    কুম
    0.36
    რთ
    0.36
    POSITIVE LOGITS
    v
    0.44
     Moonlight
    0.36
     regent
    0.35
     vittime
    0.35
     GUIDE
    0.34
     Yah
    0.34
     pianist
    0.34
     विधवा
    0.34
     femminile
    0.33
     Modem
    0.33
    Activations Density 0.028%

    No Known Activations