© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198821
    Prev
    Next
    INDEX
    Explanations

    fox

    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
     معرف
    0.38
     Mene
    0.38
     zb
    0.38
    mene
    0.38
    Sandy
    0.37
     mano
    0.37
    সপ
    0.37
     ጉ
    0.37
    emeni
    0.37
    CrossRef
    0.37
    POSITIVE LOGITS
    த்தட்ட
    0.47
    Nat
    0.43
     Ната
    0.42
     Al
    0.41
     Nat
    0.39
     Natasha
    0.39
     अनुराग
    0.39
    hormat
    0.38
    φαι
    0.37
    ይ
    0.37
    Activations Density 0.000%

    No Known Activations