© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142964
    Prev
    Next
    INDEX
    Explanations

    Chinese

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     freeze
    0.40
    Freeze
    0.38
     gaseous
    0.36
     Visions
    0.35
    multicolumn
    0.35
    rzed
    0.34
     ਰਹ
    0.34
    ወ
    0.34
    लेख
    0.34
    freeze
    0.34
    POSITIVE LOGITS
     Cherry
    0.42
    Cherry
    0.40
     Китай
    0.40
     चीनी
    0.40
    ेक्ट
    0.39
    NSInteger
    0.39
     Cherokee
    0.38
     Chin
    0.38
    ِح
    0.38
    Chinese
    0.37
    Activations Density 0.000%

    No Known Activations