© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87885
    Prev
    Next
    INDEX
    Explanations

    cancel them out

    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_23_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
    ऑस्ट्रेलिया
    0.41
     испан
    0.40
     роско
    0.40
     поиск
    0.39
     फुटबॉल
    0.39
    व
    0.38
    矛盾
    0.37
    вропей
    0.37
     ऑस्ट्रेलिया
    0.36
     иллюстрация
    0.36
    POSITIVE LOGITS
     kurt
    0.37
    glial
    0.37
     enteral
    0.36
     তুলতে
    0.35
    iamy
    0.35
    alas
    0.35
    ↵
    0.34
    ப்பா
    0.34
     pup
    0.34
    qk
    0.33
    Activations Density 0.001%

    No Known Activations