© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129662
    Prev
    Next
    INDEX
    Explanations

    code: followed by numbers or words

    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_25_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
     yaar
    0.33
     llevo
    0.32
    AAP
    0.31
    amente
    0.30
    ುದು
    0.30
    anderen
    0.29
    ecek
    0.29
    뻔
    0.29
    bala
    0.29
    лектрон
    0.29
    POSITIVE LOGITS
    だけでなく
    0.29
     molecule
    0.29
    μοί
    0.29
     fat
    0.29
     permut
    0.28
     numOf
    0.28
     permutation
    0.27
     testifies
    0.27
     compensates
    0.27
     Fat
    0.27
    Activations Density 0.000%

    No Known Activations