© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208772
    Prev
    Next
    INDEX
    Explanations

    Suggesting

    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_10_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
    ال
    0.59
    아
    0.59
    О
    0.58
    Про
    0.57
    Д
    0.55
    ה
    0.54
    Ф
    0.54
    ガ
    0.54
    Ли
    0.53
    プロ
    0.52
    POSITIVE LOGITS
     sı
    0.58
     दृष्टि
    0.50
    的环境
    0.49
     meinen
    0.46
     OI
    0.45
     Ihres
    0.45
     моего
    0.45
     dünyaya
    0.45
     सेवन
    0.44
     অর্থাৎ
    0.44
    Activations Density 0.001%

    No Known Activations