© 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. 7354
    Prev
    Next
    INDEX
    Explanations

    file index sorted

    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
     firm
    0.39
    ｃ
    0.36
    galaxy
    0.36
    鯤
    0.35
    cun
    0.34
     taxa
    0.33
    वरी
    0.33
    ^{+}
    0.33
    Retry
    0.33
    grant
    0.33
    POSITIVE LOGITS
     Deter
    0.44
    ObjectId
    0.39
     waterproofing
    0.39
    გენ
    0.39
    Sad
    0.39
     Déf
    0.38
     triang
    0.37
     Sad
    0.37
    轰
    0.37
     Excited
    0.36
    Activations Density 0.000%

    No Known Activations