© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18332
    Prev
    Next
    INDEX
    Explanations

    labs, demonstrations, simulations, practical skills

    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
     seorang
    0.51
    一座
    0.50
     derzeit
    0.47
     sehari
    0.47
     mortg
    0.46
    ון
    0.44
     homeschool
    0.44
    刳
    0.44
    研究生
    0.43
    ア
    0.43
    POSITIVE LOGITS
    र्मु
    0.54
    kk
    0.51
     patip
    0.51
     badges
    0.50
     addiction
    0.49
    then
    0.49
    evol
    0.49
    psi
    0.48
    attes
    0.48
     aromas
    0.47
    Activations Density 0.005%

    No Known Activations