© 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. 14593
    Prev
    Next
    INDEX
    Explanations

    possibly exploit

    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
     нескольких
    0.48
     Фи
    0.46
    renewcommand
    0.46
     ");
    0.46
     كتاب
    0.46
    Cannot
    0.46
    nicima
    0.45
     中
    0.44
    StringTo
    0.44
     (".
    0.44
    POSITIVE LOGITS
    bí
    0.46
    ड्यू
    0.45
    ᾖ
    0.44
    ää
    0.43
    ště
    0.42
     irão
    0.42
    מבר
    0.42
    ίζουν
    0.42
    ائی
    0.42
    וו
    0.42
    Activations Density 0.000%

    No Known Activations