© 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. 196175
    Prev
    Next
    INDEX
    Explanations

    Pathfinder/Starfinder

    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
    塩素
    0.39
    Verse
    0.37
    螨
    0.37
     خطر
    0.36
    ्टर
    0.36
    номо
    0.36
     обраща
    0.36
    硝
    0.36
    Methyl
    0.35
     uczest
    0.35
    POSITIVE LOGITS
     Orleans
    0.48
     appreciate
    0.42
     preferences
    0.40
    ouri
    0.40
    acca
    0.40
     appreciated
    0.39
     Giac
    0.39
     Renaissance
    0.39
    娴
    0.39
     apreci
    0.39
    Activations Density 0.001%

    No Known Activations