© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45025
    Prev
    Next
    INDEX
    Explanations

    common sense and commons

    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_13_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
     Geoffrey
    0.51
    ル
    0.50
     Peoples
    0.50
     Comput
    0.49
     Variety
    0.49
     Delegates
    0.48
    actyl
    0.48
     Li
    0.47
    ânea
    0.47
     पाए
    0.47
    POSITIVE LOGITS
    𝐬
    0.53
    購
    0.49
    ্সে
    0.47
    lere
    0.47
    ую
    0.46
    𝐊
    0.46
    lerinin
    0.45
    𝐟
    0.45
    禟
    0.45
    𝐦
    0.43
    Activations Density 0.001%

    No Known Activations