© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201700
    Prev
    Next
    INDEX
    Explanations

    json keys or struct fields

    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
    ير
    1.10
    ン
    1.10
    yim
    1.03
    ي
    1.01
    ли
    0.99
    يي
    0.97
    고
    0.96
    ن
    0.93
    什么
    0.92
    나
    0.91
    POSITIVE LOGITS
    j
    1.11
    ள்ளார்
    1.04
    li
    1.01
      
    0.98
    ah
    0.96
    ci
    0.92
    ino
    0.89
    ina
    0.88
    aksi
    0.86
    ના
    0.83
    Activations Density 0.002%

    No Known Activations