© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31891
    Prev
    Next
    INDEX
    Explanations

    pieces of

    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_40_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
    cdots
    0.37
    ඩි
    0.37
     다니
    0.36
    rii
    0.35
    inchi
    0.34
     ଅ
    0.33
    rinsim
    0.33
     Branch
    0.33
     Vietnam
    0.33
    靡
    0.33
    POSITIVE LOGITS
    furniture
    0.46
    equipment
    0.43
     furniture
    0.43
     फर्नीचर
    0.41
    Excuse
    0.39
     entender
    0.39
    Furniture
    0.38
    abek
    0.38
    IZING
    0.38
    eware
    0.37
    Activations Density 0.007%

    No Known Activations