© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7330
    Prev
    Next
    INDEX
    Explanations

    open file read

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [:,
    0.46
     খুঁজতে
    0.41
    )[:,
    0.40
    htim
    0.40
    찹
    0.40
     Novels
    0.38
     дома
    0.38
    óle
    0.38
     Athenian
    0.37
     bekommen
    0.37
    POSITIVE LOGITS
    avni
    0.39
    Exercise
    0.35
    Canc
    0.35
    Availability
    0.34
    Aluminum
    0.34
    Situation
    0.34
    Health
    0.33
    Between
    0.33
    樹
    0.33
    iriya
    0.33
    Activations Density 0.015%

    No Known Activations