© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177317
    Prev
    Next
    INDEX
    Explanations

    error handling

    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_29_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
     أو
    0.46
     atau
    0.46
     veya
    0.45
     oder
    0.44
     ή
    0.43
     eller
    0.42
     varsa
    0.41
     nebo
    0.41
     או
    0.40
     或者
    0.39
    POSITIVE LOGITS
     বঞ্চিত
    0.45
    従来
    0.40
    డిగా
    0.40
    షే
    0.37
    Exposure
    0.36
     уйный
    0.36
     deprive
    0.36
    AspNetUser
    0.36
     trillions
    0.36
    +)
    0.35
    Activations Density 0.003%

    No Known Activations