© 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. 201690
    Prev
    Next
    INDEX
    Explanations

    mindset

    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
     більше
    0.42
    クロス
    0.40
    বাহিনী
    0.39
     Multipart
    0.38
    廾
    0.37
     শো
    0.37
    Multipart
    0.37
     ഇടതു
    0.36
     Cross
    0.36
    cross
    0.36
    POSITIVE LOGITS
     econôm
    0.37
    ឃ
    0.36
     subarray
    0.36
     commanding
    0.35
    яна
    0.35
     Empress
    0.35
    kund
    0.35
     conferred
    0.34
    ectomy
    0.34
     antibody
    0.33
    Activations Density 0.001%

    No Known Activations