© 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. 1230
    Prev
    Next
    INDEX
    Explanations

    hundreds of tons

    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
     pineapple
    0.42
    ]._
    0.39
    冏
    0.38
    une
    0.37
     banana
    0.37
    ارم
    0.37
     economici
    0.37
     erode
    0.37
    เปอร์
    0.37
     simp
    0.37
    POSITIVE LOGITS
    百
    0.50
     whales
    0.46
     Whale
    0.46
     whale
    0.46
     Hundred
    0.43
    一百
    0.40
     Col
    0.39
     Sixty
    0.38
     Bale
    0.37
     consulté
    0.37
    Activations Density 0.011%

    No Known Activations