© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54939
    Prev
    Next
    INDEX
    Explanations

    say "i" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    搓
    0.39
    ADH
    0.36
     Nixon
    0.36
     Records
    0.35
    ocyanate
    0.34
     غم
    0.34
    লাপ
    0.33
    legas
    0.33
    ፃ
    0.33
    yntax
    0.32
    POSITIVE LOGITS
     Ist
    2.50
    Ist
    2.42
     ist
    2.33
     исто
    2.13
     IST
    2.05
    IST
    1.74
    ist
    1.73
     İst
    1.73
     stor
    1.67
    Исто
    1.59
    Activations Density 0.003%

    No Known Activations