© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124136
    Prev
    Next
    INDEX
    Explanations

    Mauryan

    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_3_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
    ید
    0.90
    ین
    0.88
    E
    0.84
    ש
    0.80
    یت
    0.79
    A
    0.78
    لی
    0.77
    ές
    0.77
    IN
    0.74
    버
    0.73
    POSITIVE LOGITS
    ри
    0.84
    ية
    0.77
    an
    0.75
    p
    0.70
    ain
    0.69
     Installation
    0.68
    på
    0.68
    li
    0.66
     for
    0.65
    ༧
    0.63
    Activations Density 0.000%

    No Known Activations