© 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. 33427
    Prev
    Next
    INDEX
    Explanations

    mixed languages

    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
     গ
    0.82
     G
    0.77
     ग
    0.67
     গড়
    0.60
     গড়
    0.55
     g
    0.53
     گ
    0.50
    G
    0.45
     Г
    0.43
    Baptiste
    0.43
    POSITIVE LOGITS
     KT
    0.44
    Raise
    0.41
     kN
    0.38
     Raises
    0.38
     applicant
    0.38
    प्र
    0.38
     chant
    0.38
     Raise
    0.38
    kN
    0.37
     raises
    0.36
    Activations Density 0.001%

    No Known Activations