© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68822
    Prev
    Next
    INDEX
    Explanations

    Ellie

    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_46_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
    侑
    0.40
    equality
    0.37
    yscy
    0.36
     equality
    0.35
     shoulder
    0.35
     Kelsey
    0.35
    obutyl
    0.35
    垣
    0.35
    IContainer
    0.34
     Jordan
    0.34
    POSITIVE LOGITS
    Sco
    0.39
    डेट
    0.38
     Sco
    0.38
    ರೆಯ
    0.38
     हरि
    0.37
     Simple
    0.37
     захо
    0.37
     מז
    0.36
     columnar
    0.36
    Eo
    0.36
    Activations Density 0.000%

    No Known Activations