© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98469
    Prev
    Next
    INDEX
    Explanations

    colleges, antemano (spanish), anime

    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_14_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
    ๊
    0.52
     expanse
    0.51
     unsuspecting
    0.50
     apologize
    0.50
     পেয়েছে
    0.50
    ால்
    0.48
     bragging
    0.48
    尒
    0.48
    ž
    0.47
     œuvre
    0.46
    POSITIVE LOGITS
    ART
    0.57
    ATH
    0.57
    AMP
    0.57
    Sh
    0.56
    e
    0.55
     ராம
    0.54
    ﺟ
    0.54
    engen
    0.52
    TikTok
    0.52
    ನಾಟಕ
    0.52
    Activations Density 0.000%

    No Known Activations