© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11042
    Prev
    Next
    INDEX
    Explanations

    molecules and RNA molecules

    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
     randomIndex
    0.53
    Ո
    0.50
     Room
    0.48
     estadísticas
    0.48
     room
    0.48
     टेबल
    0.48
    okes
    0.46
     মন্ত্রী
    0.46
    დი
    0.46
     Lowest
    0.46
    POSITIVE LOGITS
    they
    0.51
    к
    0.49
     Karne
    0.46
     они
    0.45
    those
    0.44
    疣
    0.44
     they
    0.44
    如果你
    0.44
    нки
    0.43
    updating
    0.43
    Activations Density 0.008%

    No Known Activations