© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201889
    Prev
    Next
    INDEX
    Explanations

    Norman Conquest

    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_12_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
    embrance
    0.48
     מר
    0.46
     பல்
    0.44
     シン
    0.44
    તન
    0.44
    ⵛ
    0.43
    sendKeyDown
    0.43
    ય
    0.43
     बल्ले
    0.43
     エン
    0.42
    POSITIVE LOGITS
     photocopying
    0.57
    Дата
    0.52
    Pharmaceutical
    0.51
    ﺠ
    0.50
    !).
    0.49
     Origami
    0.49
     crumpled
    0.49
    Deze
    0.48
     Pharmaceutical
    0.48
    ódromo
    0.48
    Activations Density 0.006%

    No Known Activations