© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103492
    Prev
    Next
    INDEX
    Explanations

    umami flavor

    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_1_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
    ه
    1.19
    ى
    1.18
    0
    1.16
    تش
    0.98
    ’
    0.94
    مد
    0.93
    ون
    0.92
    ل
    0.91
    ض
    0.89
    تل
    0.86
    POSITIVE LOGITS
    ING
    1.28
    s
    1.23
    ی
    1.21
    ﻣ
    1.19
    ﺔ
    1.14
     lutego
    1.12
    ﻳ
    1.12
    ing
    1.08
     fevereiro
    1.05
    き
    1.04
    Activations Density 0.000%

    No Known Activations