© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10059
    Prev
    Next
    INDEX
    Explanations

    square root

    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_13_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
    последствии
    0.46
    <0x0D>
    0.44
     giud
    0.44
    ン
    0.44
    டுக
    0.44
    šću
    0.44
     موفق
    0.43
    دت
    0.43
    にて
    0.43
    これを
    0.43
    POSITIVE LOGITS
     My
    0.43
    y
    0.43
     Chairperson
    0.43
     IN
    0.42
     bore
    0.42
     More
    0.42
     Mishra
    0.41
    AKE
    0.41
     गुलाम
    0.41
     bhave
    0.40
    Activations Density 0.123%

    No Known Activations