© 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. 13609
    Prev
    Next
    INDEX
    Explanations

    iliac arteries, actuators, Mendelian, China

    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
     decreases
    0.53
     $((
    0.52
     extreme
    0.51
     decreased
    0.50
     debido
    0.48
    の結果
    0.48
     worsens
    0.47
    㨁
    0.47
     analisar
    0.46
     waitUntil
    0.46
    POSITIVE LOGITS
    OUG
    0.48
     nyelv
    0.47
    リム
    0.46
    aric
    0.46
    гов
    0.45
    auer
    0.45
    glide
    0.44
    Henderson
    0.44
    Ж
    0.44
    ാര്യ
    0.44
    Activations Density 0.000%

    No Known Activations