© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181365
    Prev
    Next
    INDEX
    Explanations

    needs of the present without

    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_24_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     yh
    0.48
    𝒐
    0.47
     முன்னாள்
    0.46
     çünkü
    0.45
    िकुलम
    0.45
     ﺍﻟ
    0.43
    靔
    0.43
     азо
    0.43
     souh
    0.42
    ட்ர
    0.42
    POSITIVE LOGITS
    het
    0.46
     appliances
    0.43
    学的
    0.42
    -
    0.42
     পড়েছে
    0.42
    ing
    0.41
    achtree
    0.39
    asters
    0.39
    andal
    0.38
     নেত
    0.37
    Activations Density 0.000%

    No Known Activations