© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236144
    Prev
    Next
    INDEX
    Explanations

    let you know

    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_25_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
     สน
    0.46
    Inventory
    0.45
    ฟ
    0.45
     кана
    0.43
    \/}
    0.43
    Бі
    0.42
     تاب
    0.41
    랍
    0.41
     ติด
    0.41
    㴡
    0.41
    POSITIVE LOGITS
     COVID
    0.46
     solemn
    0.39
    cheiden
    0.39
     belted
    0.38
     Covid
    0.38
     solemnly
    0.37
     passes
    0.37
     vaccinated
    0.37
    chic
    0.37
     hampers
    0.36
    Activations Density 0.002%

    No Known Activations