© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42545
    Prev
    Next
    INDEX
    Explanations

    FICTION novel blueprints

    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_13_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
     competitions
    0.46
     немного
    0.46
     ihtiyaç
    0.46
    Entrance
    0.46
    |
    0.46
     newbies
    0.46
    Biografia
    0.46
     область
    0.45
    IAN
    0.45
    Original
    0.45
    POSITIVE LOGITS
    λαβ
    0.63
    섭
    0.50
    петров
    0.49
    еры
    0.48
     Wirtschafts
    0.48
     Caed
    0.48
     Herod
    0.46
    aqueous
    0.46
    ედ
    0.46
    ぶり
    0.46
    Activations Density 0.000%

    No Known Activations