© 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. 214229
    Prev
    Next
    INDEX
    Explanations

    Olympic

    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
    ுத
    0.37
    وون
    0.36
    ikaner
    0.36
     DSL
    0.35
     UG
    0.35
    েলের
    0.35
    楤
    0.35
     moelle
    0.34
    ডি
    0.34
    咂
    0.34
    POSITIVE LOGITS
     Olympic
    2.47
     olymp
    2.41
    Olymp
    2.38
    Olympic
    2.36
     ओलंपिक
    2.23
     Olympi
    2.22
    olym
    2.22
     Olympics
    2.20
     Olymp
    2.19
     olimp
    2.16
    Activations Density 0.001%

    No Known Activations