© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130709
    Prev
    Next
    INDEX
    Explanations

    measurements and precision

    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
    万
    2.20
    萬
    2.05
     万
    1.83
     만
    1.65
     thousand
    1.36
     Wan
    1.26
     Thousand
    1.20
    thousand
    1.20
    Wan
    1.15
    千
    1.13
    POSITIVE LOGITS
    ूद
    0.39
    DWARF
    0.39
    APPY
    0.38
    Diện
    0.38
    appy
    0.37
    INEN
    0.37
    渕
    0.36
    ينات
    0.35
     অপর্ণ
    0.35
     đám
    0.35
    Activations Density 0.001%

    No Known Activations