© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195002
    Prev
    Next
    INDEX
    Explanations

    asking "huh" or "eh"

    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_15_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
    厝
    0.55
    com
    0.52
     célula
    0.51
     nesta
    0.50
     डाव
    0.50
    SERVATION
    0.50
     کوم
    0.49
     com
    0.49
     घरा
    0.49
     могла
    0.49
    POSITIVE LOGITS
    ی
    0.59
     класу
    0.51
    хих
    0.49
    𝔞
    0.49
    November
    0.49
     Nietzsche
    0.47
    <0x98>
    0.47
     tattooed
    0.46
    ช
    0.46
    Ꮬ
    0.46
    Activations Density 0.001%

    No Known Activations