© 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. 201999
    Prev
    Next
    INDEX
    Explanations

    Olympus

    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
    ణులు
    0.38
     خو
    0.38
    ៤
    0.37
     LR
    0.37
     Silhouette
    0.37
     Gemini
    0.36
     Shifts
    0.36
    Church
    0.35
     لط
    0.35
     Chung
    0.35
    POSITIVE LOGITS
     fume
    0.39
     lic
    0.39
    葲
    0.38
    鴨
    0.36
    esthetic
    0.36
    滖
    0.36
    示
    0.35
    ラック
    0.35
     COUN
    0.35
    vapor
    0.35
    Activations Density 0.000%

    No Known Activations