© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14370
    Prev
    Next
    INDEX
    Explanations

    slang continuations like 'pants', 'nae', 'in', 'words'

    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_40_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
    などの
    0.43
    していた
    0.43
     শব্দটি
    0.39
     Ipsum
    0.39
    のだが
    0.39
     취
    0.38
    <sub>
    0.38
     Dolores
    0.37
    
    0.36
    ীক
    0.36
    POSITIVE LOGITS
     ain
    1.00
     gonna
    0.83
     lotta
    0.73
     goin
    0.73
     outta
    0.72
     kinda
    0.71
     gotta
    0.67
     makin
    0.66
     Ain
    0.66
    Ain
    0.65
    Activations Density 0.000%

    No Known Activations