© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129687
    Prev
    Next
    INDEX
    Explanations

    hydrostatic pressure

    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_6_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
    લ
    1.07
    ди
    1.00
    ल
    0.98
    ем
    0.91
    ق
    0.91
    ból
    0.90
    л
    0.90
    ме
    0.90
    ز
    0.89
    is
    0.88
    POSITIVE LOGITS
    </h3>
    1.05
     to
    1.05
    </strong>
    1.01
    <0x0D>
    0.99
    </h2>
    0.95
    </b>
    0.95
     been
    0.94
    </h1>
    0.93
    </a>
    0.88
    DA
    0.82
    Activations Density 0.000%

    No Known Activations