© 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. 127631
    Prev
    Next
    INDEX
    Explanations

    hate to + verb

    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
    (
    0.85
    ம்
    0.79
     cataly
    0.73
    ي
    0.73
     trouva
    0.71
    да
    0.67
    
    0.67
     intrigued
    0.67
     énorm
    0.67
     efectuar
    0.66
    POSITIVE LOGITS
    s
    0.95
    land
    0.88
    son
    0.86
    space
    0.80
    live
    0.79
    lim
    0.75
    service
    0.75
    min
    0.74
    man
    0.73
    sin
    0.73
    Activations Density 0.000%

    No Known Activations