© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33197
    Prev
    Next
    INDEX
    Explanations

    device:

    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_40_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
    
    0.37
     nonEmpty
    0.36
     obligated
    0.36
     offending
    0.35
    صميم
    0.35
    elon
    0.34
    юнча
    0.34
    णावर
    0.34
     कट
    0.33
     जैविक
    0.33
    POSITIVE LOGITS
    类
    0.37
     Uncertainty
    0.36
    引入
    0.35
    战争
    0.35
    にくい
    0.34
    arlight
    0.33
    Lantern
    0.33
     Lost
    0.32
    Velocity
    0.32
    Lost
    0.32
    Activations Density 0.003%

    No Known Activations