© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16506
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
     Incident
    0.45
     ಸಿನಿಮಾ
    0.43
     “
    0.42
     Mysterious
    0.41
    acing
    0.40
    ಲೆ
    0.40
     Jump
    0.39
     up
    0.38
     daring
    0.38
     נ
    0.38
    POSITIVE LOGITS
    வாழ்
    0.49
    ｒ
    0.46
    Бахар
    0.45
    ْر
    0.44
     használ
    0.43
    endente
    0.42
    rune
    0.41
    प्
    0.40
    ర్ణ
    0.40
     dispon
    0.39
    Activations Density 0.020%

    No Known Activations