© 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. 199088
    Prev
    Next
    INDEX
    Explanations

    void Main

    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
    /
    0.54
     moistur
    0.52
    igo
    0.50
    χεία
    0.50
     i
    0.49
     shed
    0.49
    ía
    0.48
    膊
    0.48
     mozzarella
    0.47
     el
    0.46
    POSITIVE LOGITS
    𝖑
    0.55
    𝖙
    0.55
    ತ್
    0.48
     এলিট
    0.48
     Huguen
    0.47
     डेंगू
    0.47
    saint
    0.47
    这样一个
    0.46
    !(
    0.46
     אחד
    0.45
    Activations Density 0.001%

    No Known Activations