© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35064
    Prev
    Next
    INDEX
    Explanations

    non-English syllables

    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_3_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
    ت
    1.38
    ك
    1.11
    um
    1.06
    م
    1.01
    ل
    0.95
    大
    0.92
    تك
    0.91
    2
    0.89
    ur
    0.88
    。
    0.87
    POSITIVE LOGITS
    ia
    0.84
    र्स
    0.83
    น
    0.82
    рены
    0.82
    ینی
    0.76
     luj
    0.75
    ων
    0.74
    ษ
    0.74
     lulus
    0.73
     polizia
    0.72
    Activations Density 0.003%

    No Known Activations