© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210690
    Prev
    Next
    INDEX
    Explanations

    code parameters: property, column, cell, field

    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_20_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
    sat
    0.37
    我们将
    0.35
    k
    0.34
    我们会
    0.34
     Delegates
    0.32
     Through
    0.32
    bride
    0.32
    这将
    0.31
     х
    0.31
    lm
    0.31
    POSITIVE LOGITS
     approu
    0.34
     মুক্তিব
    0.31
    েন্ত্র
    0.31
     psychologist
    0.30
     codon
    0.30
     ইসলামাবাদের
    0.29
     በጣም
    0.29
     Physik
    0.29
     chemins
    0.29
     hydrox
    0.29
    Activations Density 0.001%

    No Known Activations