© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257240
    Prev
    Next
    INDEX
    Explanations

    combinations and sampling

    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_22_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
    AW
    0.46
    Errorf
    0.42
    Poster
    0.41
    库
    0.41
    Keyboard
    0.40
    जय
    0.39
    یت
    0.39
    WS
    0.39
    テク
    0.38
    废
    0.37
    POSITIVE LOGITS
     చేసిన
    0.49
    phalt
    0.45
     முக்கியமான
    0.45
     Nachhalt
    0.44
    
    0.44
     ಸಂಖ್ಯ
    0.43
     ಮಾಡಿದ
    0.43
     महापौर
    0.43
     પ્રતિબિં
    0.42
     Jahn
    0.42
    Activations Density 0.001%

    No Known Activations