© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120243
    Prev
    Next
    INDEX
    Explanations

    lists, plus, above, criteria

    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_27_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
     теории
    0.42
     sadrž
    0.40
     chứa
    0.38
    Ь
    0.37
    teach
    0.36
     CONTAIN
    0.36
    пикир
    0.35
    ourses
    0.34
     teoría
    0.34
     содержание
    0.33
    POSITIVE LOGITS
    ക്കിയി
    0.39
     differently
    0.38
    agements
    0.38
     አይነት
    0.37
    堭
    0.37
    দেশে
    0.36
     very
    0.36
    谓
    0.35
     experiencing
    0.35
     frequently
    0.35
    Activations Density 0.001%

    No Known Activations