© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85355
    Prev
    Next
    INDEX
    Explanations

    csv reader

    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_23_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
    玤
    0.46
     تجرب
    0.44
    圤
    0.41
     अल
    0.41
     уверен
    0.41
     कैंडिडेट्स
    0.41
    aysa
    0.40
     смесь
    0.39
    ರ್‌
    0.39
    丄
    0.38
    POSITIVE LOGITS
     soon
    0.50
     decid
    0.45
     protagonist
    0.45
     protagonists
    0.45
     decide
    0.45
     refuse
    0.43
     stifle
    0.43
     inter
    0.43
     off
    0.41
     specialist
    0.41
    Activations Density 0.000%

    No Known Activations