© 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. 227929
    Prev
    Next
    INDEX
    Explanations

    同路, 同人, 同心

    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
    ين
    1.07
    ل
    0.83
    ني
    0.82
    ص
    0.81
    اء
    0.78
    ق
    0.77
    л
    0.76
    رك
    0.74
    ى
    0.74
    ל
    0.73
    POSITIVE LOGITS
    '
    1.02
    (
    0.83
    ↵
    0.76
    <0x80>
    0.76
     to
    0.71
    mmol
    0.65
    0
    0.64
    ۰
    0.64
    HEN
    0.61
    K
    0.59
    Activations Density 0.001%

    No Known Activations