© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136137
    Prev
    Next
    INDEX
    Explanations

    arsenal odds football goalkeeper

    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_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bou
    0.60
    و
    0.59
    odob
    0.55
    ೂ
    0.55
    ğ
    0.55
    يد
    0.53
    。
    0.51
    )،
    0.51
    ו
    0.51
     carácter
    0.50
    POSITIVE LOGITS
     Dương
    0.50
    ेबल
    0.49
    ς
    0.48
     unite
    0.47
    klahoma
    0.47
     MTLTexture
    0.47
     പുതു
    0.46
    𝐁
    0.46
    tw
    0.46
     सी
    0.46
    Activations Density 0.000%

    No Known Activations