© 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. 138668
    Prev
    Next
    INDEX
    Explanations

    archival quality

    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
     acidic
    0.68
    кисло
    0.62
     кисло
    0.60
    酸
    0.60
     кислоты
    0.56
     acide
    0.55
     acids
    0.55
     acid
    0.54
     ácido
    0.53
     Acid
    0.52
    POSITIVE LOGITS
     incurring
    0.43
    Centers
    0.38
    が出る
    0.38
    鄂
    0.38
     outpost
    0.37
    סטר
    0.36
     Spur
    0.35
     eaves
    0.35
     frat
    0.35
     Spiritual
    0.34
    Activations Density 0.000%

    No Known Activations