© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203356
    Prev
    Next
    INDEX
    Explanations

    Show me

    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_25_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
    눔
    0.39
     protector
    0.37
     saddhim
    0.36
    壟
    0.36
    堭
    0.36
     رنگ
    0.36
     puriso
    0.35
     Oceanic
    0.35
     राज्यसभा
    0.35
     painter
    0.34
    POSITIVE LOGITS
     TOE
    0.39
    ግር
    0.38
    uš
    0.38
     पड़
    0.37
    lu
    0.35
    ادف
    0.35
    сто
    0.34
    艘
    0.34
    \".
    0.33
    McG
    0.33
    Activations Density 0.003%

    No Known Activations