© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45823
    Prev
    Next
    INDEX
    Explanations

    quotation marks and code delimiters

    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_22_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
    größe
    0.28
    ofs
    0.27
    ㌔
    0.26
    Ꮡ
    0.26
     kaisi
    0.25
    ட்சய
    0.24
    зили
    0.24
     bahut
    0.24
    استشهاد
    0.24
    鷸
    0.24
    POSITIVE LOGITS
    都能
    0.22
    灌
    0.22
    気軽に
    0.22
     shield
    0.22
     seeker
    0.22
     Auer
    0.22
     সিস্ট
    0.21
     imperme
    0.21
     overcame
    0.21
     جوړونکي
    0.21
    Activations Density 0.058%

    No Known Activations