© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197486
    Prev
    Next
    INDEX
    Explanations

    plan, argument, publicly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
    s
    0.76
    sion
    0.55
    t
    0.52
     número
    0.50
    f
    0.50
    lar
    0.49
     zaključ
    0.49
    summary
    0.48
     família
    0.48
    dance
    0.47
    POSITIVE LOGITS
    柤
    0.52
    ามารถ
    0.48
    ANGAN
    0.43
    捙
    0.42
    ופ
    0.41
    ↙
    0.41
    +}$
    0.40
     RESERVE
    0.40
    尭
    0.39
    ٹو
    0.39
    Activations Density 0.000%

    No Known Activations