© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86965
    Prev
    Next
    INDEX
    Explanations

    Youngtimer, Ynet, Yoneda, Yield GAP

    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_3_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
     μία
    0.67
    uk
    0.64
    ug
    0.64
    iert
    0.63
    ud
    0.61
    im
    0.58
    ι
    0.58
     написа
    0.57
     ملي
    0.57
    ᅵ
    0.57
    POSITIVE LOGITS
     of
    0.86
    스
    0.81
    지
    0.79
    तक
    0.72
    of
    0.69
    מי
    0.69
    सी
    0.68
    ス
    0.68
    сті
    0.67
    ของ
    0.66
    Activations Density 0.000%

    No Known Activations