© 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. 138372
    Prev
    Next
    INDEX
    Explanations

    individual or group interaction

    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
     izra
    0.42
    vist
    0.38
    )(=
    0.35
    wärts
    0.35
    ALLOW
    0.35
     ocurrido
    0.35
     REQUIRE
    0.35
    vis
    0.34
     aur
    0.34
     dış
    0.34
    POSITIVE LOGITS
    組
    0.38
     weiterhin
    0.37
     რომლებიც
    0.36
     borrowed
    0.35
     Brou
    0.35
     하다
    0.35
    ပြန်
    0.35
    redni
    0.33
    Neder
    0.33
    CommonAncestor
    0.33
    Activations Density 0.004%

    No Known Activations