© 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. 228299
    Prev
    Next
    INDEX
    Explanations

    Qin Shi Huang

    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
    ى
    0.98
     in
    0.97
    ли
    0.97
    т
    0.92
    <0x80>
    0.87
    х
    0.86
    ྥ
    0.86
     unrecognizable
    0.83
     وإن
    0.81
     alcanz
    0.80
    POSITIVE LOGITS
    i
    1.47
    at
    1.24
    ה
    1.21
    us
    1.16
    a
    1.16
    :
    1.15
    2
    1.12
    ทั้งหมด
    1.09
    IB
    1.09
    ING
    1.07
    Activations Density 0.000%

    No Known Activations