© 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. 31265
    Prev
    Next
    INDEX
    Explanations

    Greek language

    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
    ге
    0.42
    次方
    0.41
     ಲ
    0.40
     ליי
    0.40
     Tul
    0.40
     er
    0.39
     안
    0.39
    텀
    0.39
    TI
    0.39
    хай
    0.38
    POSITIVE LOGITS
     কিলো
    0.45
    멧
    0.45
     Metz
    0.42
    toString
    0.41
     στ
    0.41
     Smiths
    0.40
    ToString
    0.39
    スト
    0.39
     barrel
    0.39
     क्रिस
    0.38
    Activations Density 0.000%

    No Known Activations