© 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. 55046
    Prev
    Next
    INDEX
    Explanations

    scientific units

    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
    LayoutParams
    0.38
     letters
    0.38
     printer
    0.37
     ㄱ
    0.37
     lettres
    0.36
    ութ
    0.36
    marginLeft
    0.36
    
    0.35
    കളുടെ
    0.35
     LETTERS
    0.35
    POSITIVE LOGITS
    ھیں
    0.45
    гнозы
    0.40
    interested
    0.39
     frankly
    0.36
     OTP
    0.35
    ζα
    0.35
     Med
    0.35
    satisf
    0.34
    ходи
    0.34
    гноз
    0.34
    Activations Density 0.002%

    No Known Activations