© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39137
    Prev
    Next
    INDEX
    Explanations

    Drunk, substance, alcohol

    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
    ě
    0.46
    ued
    0.45
    scrire
    0.42
    ra
    0.42
    ően
    0.42
     dea
    0.40
    ικό
    0.40
    igenschaften
    0.39
     QMessageBox
    0.39
     freed
    0.39
    POSITIVE LOGITS
    diabetes
    0.49
     payday
    0.48
     cerveza
    0.46
     ডিজি
    0.44
     by
    0.44
    __()
    0.44
    INDU
    0.44
     Díaz
    0.43
     Camin
    0.43
     backpacking
    0.43
    Activations Density 0.034%

    No Known Activations