© 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. 139234
    Prev
    Next
    INDEX
    Explanations

    names and their suffixes

    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
    ProductRunnable
    0.43
    strument
    0.39
    รือ
    0.39
     ಮನೆಯ
    0.39
    扼
    0.38
     мне
    0.38
     trilogy
    0.38
    GAL
    0.38
    ULU
    0.37
    郓
    0.37
    POSITIVE LOGITS
     Professor
    0.37
     comparable
    0.36
     นาย
    0.36
     জনাব
    0.35
     Had
    0.34
    ilaire
    0.34
     அவ
    0.34
    Professor
    0.33
    urit
    0.33
     (-
    0.33
    Activations Density 0.005%

    No Known Activations