© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57801
    Prev
    Next
    INDEX
    Explanations

    pre

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    training
    0.49
    entraînement
    0.46
     प्रशिक्षण
    0.45
    steak
    0.45
    Ⲑ
    0.45
     ट्रेनिंग
    0.44
    train
    0.41
    訓練
    0.41
    GetAll
    0.41
    MaxPooling
    0.40
    POSITIVE LOGITS
     no
    0.57
     pre
    0.50
     sold
    0.45
     deleg
    0.43
    No
    0.43
     ~\
    0.42
     few
    0.42
    ～
    0.42
    no
    0.42
    ~
    0.42
    Activations Density 0.005%

    No Known Activations