© 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. 237005
    Prev
    Next
    INDEX
    Explanations

    take

    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
     Guy
    0.40
     dịp
    0.38
    Hak
    0.37
    的作品
    0.37
    Guy
    0.36
    ikut
    0.35
     Robins
    0.35
    핸
    0.35
     شغ
    0.34
     пы
    0.34
    POSITIVE LOGITS
     मिळाली
    0.38
    genommen
    0.38
     genomen
    0.38
    conde
    0.37
     Nal
    0.37
     take
    0.36
     nehmen
    0.36
     gotten
    0.36
     semic
    0.36
     በቀ
    0.36
    Activations Density 0.001%

    No Known Activations