© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36613
    Prev
    Next
    INDEX
    Explanations

    bookish, literary, and RPG related content

    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_11_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
    7
    0.52
    5
    0.52
    al
    0.49
    6
    0.49
    3
    0.45
    4
    0.44
    、
    0.44
     -
    0.43
    ou
    0.42
     (
    0.42
    POSITIVE LOGITS
    Muh
    0.40
    지는
    0.40
     많은
    0.40
    ERICAN
    0.40
    ಗ್ರ
    0.40
    जीर
    0.39
     trình
    0.39
     många
    0.39
    зяржа
    0.39
    AK
    0.39
    Activations Density 0.024%

    No Known Activations