© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29835
    Prev
    Next
    INDEX
    Explanations

    fortify or strengthen

    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_10_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
    ك
    0.78
    म
    0.77
    ن
    0.74
    я
    0.70
    ન
    0.66
    t
    0.66
    ligi
    0.65
    bergs
    0.63
    ка
    0.63
    CTION
    0.63
    POSITIVE LOGITS
     on
    0.66
     धनिया
    0.61
     conciencia
    0.59
     desej
    0.58
    ۔
    0.58
     onboarding
    0.58
    。《
    0.57
    ówczas
    0.57
     náklady
    0.56
    ﻧ
    0.56
    Activations Density 0.000%

    No Known Activations