© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171494
    Prev
    Next
    INDEX
    Explanations

    minimum viable product

    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_20_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
    ਤ
    0.35
    than
    0.35
    it
    0.33
    tham
    0.32
    appointment
    0.32
    calculate
    0.32
    **
    0.32
    #'
    0.32
    ත
    0.32
    path
    0.32
    POSITIVE LOGITS
    เนื่อง
    0.42
     అందించ
    0.36
     України
    0.36
    嗶
    0.36
     অন্যান্য
    0.35
     supplying
    0.34
     викона
    0.34
     จาก
    0.33
     공급
    0.33
     установлено
    0.32
    Activations Density 0.038%

    No Known Activations