© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203417
    Prev
    Next
    INDEX
    Explanations

    .xd text

    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_25_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
    entering
    0.26
     playing
    0.25
     Tob
    0.25
     chipping
    0.25
    occupied
    0.25
     taking
    0.24
     confronted
    0.24
    ই
    0.24
    playing
    0.24
    //!
    0.24
    POSITIVE LOGITS
     goutte
    0.26
     Kasım
    0.25
    滤
    0.25
     نوفمبر
    0.24
    ၎
    0.24
     Auflage
    0.24
    おすすめです
    0.24
    ման
    0.24
     Например
    0.23
     высоте
    0.23
    Activations Density 0.004%

    No Known Activations