© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14303
    Prev
    Next
    INDEX
    Explanations

    waiter, attendant, Gothic, horror

    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
    슌
    0.19
    ln
    0.19
    точ
    0.19
    邑
    0.18
    фин
    0.18
    ᆫ
    0.18
    。",
    0.18
    টল
    0.17
    زين
    0.17
     ڕۆ
    0.17
    POSITIVE LOGITS
     para
    0.23
     datac
    0.20
     paragraph
    0.20
     training
    0.20
     piattaforma
    0.20
     dall
    0.19
     header
    0.19
     dining
    0.19
     dalle
    0.19
     Para
    0.19
    Activations Density 0.011%

    No Known Activations