© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181788
    Prev
    Next
    INDEX
    Explanations

    Starts phrases or describes benefits

    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_29_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
     চট্টগ্রাম
    0.42
    களில்
    0.38
    arda
    0.37
    她
    0.37
    郑
    0.36
     മുഖ്യമ
    0.36
     ఆమె
    0.36
     ഒരു
    0.35
     बेंगल
    0.35
    诶
    0.35
    POSITIVE LOGITS
    خير
    0.40
     ير
    0.38
    Luckily
    0.37
     This
    0.35
     Fib
    0.35
    进制
    0.34
    convex
    0.34
     générale
    0.34
    CONSOLE
    0.34
    ประกอบ
    0.34
    Activations Density 0.000%

    No Known Activations