© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194576
    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_15_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
    Ẳ
    0.60
     AppBsky
    0.57
     Caribe
    0.57
     الأه
    0.57
     canaux
    0.55
     свадь
    0.55
     вимо
    0.55
     Carls
    0.53
    وريا
    0.53
     Brito
    0.53
    POSITIVE LOGITS
     be
    0.57
    import
    0.54
    ly
    0.52
     stunning
    0.50
    ld
    0.49
     —
    0.49
    ',
    0.48
     computer
    0.48
    —
    0.48
    name
    0.48
    Activations Density 0.001%

    No Known Activations