© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1907
    Prev
    Next
    INDEX
    Explanations

    universities and research institutions

    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_39_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
     नियामक
    0.41
     आइकॉन
    0.40
    птовалю
    0.39
     regulatory
    0.39
    យក
    0.38
    鬣
    0.38
     सूत्र
    0.37
     fournisseur
    0.37
    醣
    0.37
     differentiation
    0.37
    POSITIVE LOGITS
    Harvard
    0.66
     MIT
    0.64
    Stanford
    0.64
    MIT
    0.63
     Pew
    0.63
     Harvard
    0.62
     Brookings
    0.61
     NPR
    0.59
     Stanford
    0.59
    TED
    0.57
    Activations Density 0.051%

    No Known Activations