© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34508
    Prev
    Next
    INDEX
    Explanations

    skin health and changes

    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_3_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
    ם
    0.78
    कम
    0.59
     Rapp
    0.57
     Midlands
    0.57
     Tia
    0.57
    bott
    0.57
     T
    0.56
     We
    0.56
    ן
    0.55
     Mog
    0.55
    POSITIVE LOGITS
     önüne
    0.65
    ༢
    0.64
     función
    0.63
    ﺪ
    0.63
     garnished
    0.62
     dată
    0.61
    ﺍ
    0.61
    ية
    0.60
     murdered
    0.59
     as
    0.59
    Activations Density 0.006%

    No Known Activations