© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24587
    Prev
    Next
    INDEX
    Explanations

    O

    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_56_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
    rological
    0.38
    રોના
    0.38
     ～
    0.37
     ㅣ
    0.37
    टीएम
    0.36
    ァ
    0.36
     aeros
    0.35
    ｱ
    0.35
    టీఎం
    0.35
    ﺎ
    0.35
    POSITIVE LOGITS
     o
    0.91
     о
    0.75
    ᧐
    0.69
    ⲟ
    0.68
    о
    0.68
    𝚘
    0.67
    ō
    0.65
    
    0.64
    オ
    0.64
    ߋ
    0.63
    Activations Density 0.179%

    No Known Activations