© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32016
    Prev
    Next
    INDEX
    Explanations

    EMIEW followed by number

    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_7_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
     conducir
    0.24
     связанные
    0.23
     strane
    0.22
    ۰۰
    0.22
     мно
    0.21
    [];
    0.21
     رجل
    0.20
    ﻻ
    0.20
    Ԁ
    0.20
     provocar
    0.20
    POSITIVE LOGITS
    ل
    0.39
    t
    0.32
    l
    0.31
    </h2>
    0.31
    s
    0.31
    し
    0.29
    ما
    0.28
    ب
    0.28
    r
    0.28
    ر
    0.28
    Activations Density 0.001%

    No Known Activations