© 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. 31770
    Prev
    Next
    INDEX
    Explanations

    Kazakhstan

    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
     Aver
    0.41
     compone
    0.39
    ゐ
    0.39
    ূর্ণ
    0.38
     हनुमान
    0.37
     रानी
    0.37
    торами
    0.37
    同樣
    0.37
    َي
    0.36
    Tiger
    0.36
    POSITIVE LOGITS
    akh
    0.67
    akkh
    0.52
    akah
    0.51
    ak
    0.50
    اخ
    0.49
    ack
    0.49
    坂
    0.46
    akas
    0.45
    acal
    0.44
    PIO
    0.44
    Activations Density 0.006%

    No Known Activations