© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88435
    Prev
    Next
    INDEX
    Explanations

    CouchDB and potatoes

    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
    ou
    0.75
    k
    0.67
    מ
    0.65
    បែ
    0.59
    其他
    0.58
    要
    0.58
    و
    0.58
    ל
    0.57
    على
    0.57
    خ
    0.57
    POSITIVE LOGITS
    й
    0.72
    _
    0.71
    ″]
    0.68
    ری
    0.66
    름
    0.65
    ه‌ای
    0.63
    _'.$
    0.63
    दमी
    0.63
    یس
    0.63
    هایی
    0.63
    Activations Density 0.000%

    No Known Activations