© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62446
    Prev
    Next
    INDEX
    Explanations

    proud of

    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_11_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
    j
    0.71
    ̌
    0.54
    chten
    0.52
    нти
    0.50
     Chry
    0.50
     Desember
    0.50
    jelen
    0.49
     Smit
    0.49
    raviolet
    0.48
     perfe
    0.48
    POSITIVE LOGITS
     ਨਹੀਂ
    0.56
    𝑀
    0.54
     рэгістра
    0.52
    鏖
    0.52
     aparelho
    0.51
     câncer
    0.50
    はない
    0.50
     arrivée
    0.50
     atteinte
    0.50
     الار
    0.50
    Activations Density 0.001%

    No Known Activations