© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69796
    Prev
    Next
    INDEX
    Explanations

    specific entities

    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_51_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
     নাইট
    0.40
    ཏ
    0.40
    டம்
    0.40
     改
    0.38
    gne
    0.38
    ⑰
    0.37
    েনা
    0.36
     शुरुआ
    0.36
     চেন
    0.35
     मम
    0.35
    POSITIVE LOGITS
     RÉ
    0.75
     Ré
    0.70
     Ví
    0.70
    ví
    0.68
     Á
    0.68
    Á
    0.67
    lé
    0.67
     ví
    0.66
    Ré
    0.64
    GÁ
    0.63
    Activations Density 0.001%

    No Known Activations