© 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. 215387
    Prev
    Next
    INDEX
    Explanations

    Patrick Mahomes

    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
    ப்பி
    0.46
     psi
    0.38
    ྟ
    0.38
    }'.
    0.37
     दोगु
    0.37
    serializer
    0.36
    ISER
    0.36
     Oro
    0.36
     Mich
    0.36
     अधि
    0.36
    POSITIVE LOGITS
     Zah
    0.41
     E
    0.40
     Daniel
    0.40
    Daniel
    0.40
    знав
    0.38
     الك
    0.38
     Elias
    0.38
    الك
    0.38
    KOH
    0.37
    Koh
    0.37
    Activations Density 0.000%

    No Known Activations