© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7183
    Prev
    Next
    INDEX
    Explanations

    version or versions

    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_39_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
    酒店
    0.43
    陉
    0.42
    睡眠
    0.41
    详解
    0.39
    盻
    0.39
     호텔
    0.38
    道府県
    0.38
    炀
    0.38
    غت
    0.37
     Explained
    0.37
    POSITIVE LOGITS
    version
    0.51
     version
    0.47
    VERSION
    0.45
    Version
    0.45
     نسخه
    0.41
     numerically
    0.38
     versions
    0.38
    prevent
    0.38
    latest
    0.37
     patch
    0.37
    Activations Density 0.040%

    No Known Activations