© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42720
    Prev
    Next
    INDEX
    Explanations

    cuneiform, kundalini, condom

    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_3_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
    ين
    0.75
    تين
    0.75
    عة
    0.74
    تي
    0.72
    كلة
    0.67
    ارين
    0.67
     zusammen
    0.64
    <0x9E>
    0.62
    ضي
    0.62
    عين
    0.62
    POSITIVE LOGITS
    is
    0.80
     ک
    0.70
     ต
    0.68
    ນະ
    0.67
    روی
    0.67
    isn
    0.66
    an
    0.65
    ile
    0.64
     ی
    0.64
    ूर
    0.64
    Activations Density 0.001%

    No Known Activations