© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27571
    Prev
    Next
    INDEX
    Explanations

    User class or Employee

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    張
    0.34
     подтвер
    0.32
     하루
    0.32
    也不能
    0.30
     확인할
    0.30
    张
    0.30
     जहाँ
    0.30
    шей
    0.30
     호
    0.29
    oppers
    0.29
    POSITIVE LOGITS
     Ro
    0.35
     Walla
    0.35
     nắm
    0.33
     aliqu
    0.32
     pase
    0.32
     Event
    0.31
     Montserrat
    0.31
     সাল
    0.31
     inner
    0.30
     frank
    0.30
    Activations Density 0.004%

    No Known Activations