© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131358
    Prev
    Next
    INDEX
    Explanations

    you

    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_50_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
     szín
    0.41
    ipherals
    0.40
     affirmations
    0.40
     домаћинствима
    0.39
    亚
    0.39
    ურნ
    0.37
     my
    0.37
     Poison
    0.37
     Winifred
    0.37
    燼
    0.37
    POSITIVE LOGITS
    рачи
    0.40
    Dani
    0.38
    Tub
    0.38
    orschung
    0.37
     сер
    0.37
    Dee
    0.37
    fee
    0.37
    olio
    0.36
     deacetyl
    0.35
     دل
    0.34
    Activations Density 0.002%

    No Known Activations