© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39247
    Prev
    Next
    INDEX
    Explanations

    technical context

    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_57_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
     L
    0.63
    dt
    0.58
    Dt
    0.57
     t
    0.55
     AH
    0.54
    L
    0.54
    gt
    0.49
     AG
    0.48
     الل
    0.48
    Ｌ
    0.48
    POSITIVE LOGITS
     T
    1.08
     Т
    1.02
     الت
    0.98
     Τ
    0.91
     टी
    0.85
     টি
    0.77
     הט
    0.76
     ಟ
    0.75
     TI
    0.74
     Та
    0.73
    Activations Density 0.000%

    No Known Activations