© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132341
    Prev
    Next
    INDEX
    Explanations

    bh, Bhar, Bh variants

    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_6_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
     tradu
    1.25
    ﺍ
    1.17
     livré
    1.15
     válida
    1.12
     criado
    1.12
    ﺭ
    1.12
    ﻥ
    1.12
     contrat
    1.11
     francés
    1.11
     testify
    1.09
    POSITIVE LOGITS
    a
    1.27
    d
    1.24
    in
    1.19
    د
    1.19
    t
    1.13
    inflammatory
    1.10
    س
    1.06
    də
    1.04
    ir
    1.03
    و
    1.02
    Activations Density 0.000%

    No Known Activations