© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66658
    Prev
    Next
    INDEX
    Explanations

    York

    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_41_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
    explanatory
    0.45
     लगना
    0.39
     Ta
    0.37
    鉭
    0.37
     destinée
    0.37
     kur
    0.36
     lans
    0.36
    kur
    0.35
    덱
    0.35
    뷊
    0.35
    POSITIVE LOGITS
     Yorkshire
    0.46
    ◇
    0.41
    志愿
    0.40
     Yor
    0.40
    स्पद
    0.38
     ćel
    0.38
     Middlesbrough
    0.38
     whit
    0.37
     YORK
    0.37
     hagg
    0.37
    Activations Density 0.000%

    No Known Activations