© 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. 13266
    Prev
    Next
    INDEX
    Explanations

    Character names and titles

    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
    रित
    0.41
    inare
    0.41
    ทร
    0.39
     অঙ্গ
    0.38
     शोर
    0.38
     punctured
    0.38
    =}
    0.36
    ัป
    0.36
     черно
    0.35
    areth
    0.35
    POSITIVE LOGITS
    Bene
    0.45
     Peach
    0.41
     Sap
    0.40
     Tsun
    0.40
     শাল
    0.39
    ående
    0.39
     Kun
    0.39
     Gravity
    0.38
    Peach
    0.38
     Bene
    0.37
    Activations Density 0.047%

    No Known Activations