© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13464
    Prev
    Next
    INDEX
    Explanations

    doing a favor

    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
    ♂
    0.52
     சம்ப
    0.49
    পতি
    0.48
     Pertama
    0.47
     basking
    0.47
    atique
    0.47
     Futuristic
    0.47
     সপ্তাহ
    0.46
    iencia
    0.46
     完全
    0.45
    POSITIVE LOGITS
    ﾝ
    0.54
    at
    0.52
    h
    0.51
     завода
    0.50
    ବ
    0.50
    त
    0.48
    rng
    0.48
     minim
    0.48
    ួក
    0.48
     necessari
    0.48
    Activations Density 0.000%

    No Known Activations