© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107441
    Prev
    Next
    INDEX
    Explanations

    Persian

    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_2_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
    a
    1.11
    ir
    0.98
    il
    0.93
    ug
    0.91
    ine
    0.85
    ia
    0.83
    o
    0.81
    ва
    0.80
    j
    0.80
    ab
    0.74
    POSITIVE LOGITS
    ية
    0.92
    ス
    0.87
    ят
    0.86
    ﺍ
    0.86
    кам
    0.84
    д
    0.82
    ка
    0.78
    ють
    0.77
    deki
    0.76
    み
    0.75
    Activations Density 0.000%

    No Known Activations