© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65942
    Prev
    Next
    INDEX
    Explanations

    gunpla, model painting

    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_41_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
    ആര്‍
    0.44
     جیک
    0.42
     यूनिवर्सल
    0.42
     Чар
    0.39
    睡觉
    0.38
    jacke
    0.38
    톰
    0.38
     ziy
    0.38
    世紀
    0.37
    薬
    0.37
    POSITIVE LOGITS
    覇
    0.40
    කි
    0.40
     Runners
    0.40
    嶺
    0.39
    smith
    0.37
     thresh
    0.37
    锲
    0.37
    runner
    0.37
    ampions
    0.36
    Fro
    0.35
    Activations Density 0.001%

    No Known Activations