© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126776
    Prev
    Next
    INDEX
    Explanations

    when it is

    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_37_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
     nơi
    1.54
     places
    1.45
     tempat
    1.45
    的地方
    1.41
     곳
    1.41
    場所
    1.37
     where
    1.36
     مكان
    1.35
     lugar
    1.34
     place
    1.34
    POSITIVE LOGITS
    什
    0.40
     النوع
    0.37
    種類
    0.37
    ྒ
    0.37
     வக
    0.36
    bigvee
    0.35
     त्याचे
    0.35
     آنچه
    0.35
     ways
    0.34
    形式
    0.34
    Activations Density 0.038%

    No Known Activations