© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17548
    Prev
    Next
    INDEX
    Explanations

    strong emphasis

    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
     unui
    0.56
    栻
    0.54
    ﻜ
    0.51
    ബന്ധ
    0.50
    ради
    0.48
    மர
    0.48
    బర్
    0.48
     Weeks
    0.48
     vytvá
    0.48
    㠱
    0.48
    POSITIVE LOGITS
    expired
    0.50
     کھیلتے
    0.49
     כש
    0.48
    ี่
    0.47
    ção
    0.47
    íssimo
    0.46
     כי
    0.45
     کھیلنے
    0.45
    teis
    0.45
     subdued
    0.44
    Activations Density 0.064%

    No Known Activations