© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220347
    Prev
    Next
    INDEX
    Explanations

    page URL parameter

    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_31_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
     ಸಂಗ
    0.37
    辅
    0.35
     رفته
    0.35
     ناول
    0.35
    राने
    0.34
     অস্তিত্ব
    0.34
     કબ
    0.33
    Thu
    0.33
    யில்
    0.33
     Feuer
    0.32
    POSITIVE LOGITS
     springfox
    0.38
     paces
    0.37
     formality
    0.36
    ⅱ
    0.36
     sites
    0.35
     seven
    0.33
    ⅰ
    0.33
    IServer
    0.33
     airports
    0.33
     functionalities
    0.33
    Activations Density 0.001%

    No Known Activations