© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215472
    Prev
    Next
    INDEX
    Explanations

    say "type"

    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_50_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
     রাসেল
    0.40
     Kib
    0.40
    atamente
    0.38
    畐
    0.38
    તી
    0.38
    敀
    0.37
     ક્
    0.37
     QH
    0.37
     Qg
    0.36
     большие
    0.36
    POSITIVE LOGITS
     ivvu
    0.38
    なさ
    0.38
     näher
    0.37
    LOADSTRING
    0.37
    __()
    0.36
    লম্ব
    0.36
     pws
    0.36
     नाट
    0.36
    ExposureTime
    0.36
    聋
    0.35
    Activations Density 0.001%

    No Known Activations