© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120786
    Prev
    Next
    INDEX
    Explanations

    unity scene setup

    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_27_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
     다
    0.39
     διαφο
    0.38
     प्रस
    0.38
    사와
    0.38
    ガラ
    0.37
    峀
    0.36
     inwardly
    0.35
     calibrate
    0.35
    క్టర్
    0.35
     juxtap
    0.34
    POSITIVE LOGITS
    授权
    0.40
     prepayment
    0.39
    穿着
    0.38
     perí
    0.38
    叙
    0.38
     النساء
    0.37
    க்கூடாது
    0.36
     lasciato
    0.36
     نص
    0.36
    ৪৩
    0.35
    Activations Density 0.001%

    No Known Activations