© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63298
    Prev
    Next
    INDEX
    Explanations

    a

    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_46_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
     buy
    0.50
    买
    0.49
    buy
    0.47
    買
    0.44
     Buy
    0.44
    Buy
    0.43
     lie
    0.39
    贵
    0.38
    貴
    0.37
    ভারত
    0.37
    POSITIVE LOGITS
     techs
    0.42
     क्षेत्रों
    0.40
     tsp
    0.39
     ಏನ
    0.38
    mette
    0.38
     tek
    0.38
     प्राचीन
    0.37
     commits
    0.37
    blowing
    0.36
    ৭০
    0.36
    Activations Density 0.001%

    No Known Activations