© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216198
    Prev
    Next
    INDEX
    Explanations

    ro variations

    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_50_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
     குவி
    0.38
    廊
    0.37
     Kore
    0.37
     יע
    0.36
    Jose
    0.36
    קור
    0.35
    իր
    0.34
    ="_
    0.34
     кори
    0.34
    hexagon
    0.34
    POSITIVE LOGITS
     ро
    1.66
     ro
    1.60
     rog
    1.23
     Rog
    1.23
     로
    1.12
     رو
    1.10
    Rog
    1.09
     Ro
    1.06
     रो
    1.03
     Ро
    1.03
    Activations Density 0.001%

    No Known Activations