© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107713
    Prev
    Next
    INDEX
    Explanations

    diarrhea

    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_1_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
    al
    1.11
    نګه
    0.99
    ື່ອງ
    0.98
    okban
    0.97
    紆
    0.94
    DrvGPIO
    0.92
    ாதார
    0.92
    ாலும்
    0.91
    hwa
    0.91
     едно
    0.91
    POSITIVE LOGITS
    ED
    1.85
    ER
    1.82
    AN
    1.65
    A
    1.58
    It
    1.57
    AT
    1.52
    0
    1.48
    IT
    1.45
    EL
    1.41
    AR
    1.41
    Activations Density 0.001%

    No Known Activations