© 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. 133923
    Prev
    Next
    INDEX
    Explanations

    igneous and sedimentary rocks

    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
    </h3>
    1.25
    -
    1.08
    you
    0.98
    ut
    0.96
    at
    0.91
    erm
    0.91
    ↵
    0.90
    cH
    0.90
    </h1>
    0.88
    iv
    0.86
    POSITIVE LOGITS
     of
    1.10
    ال
    1.09
     and
    1.02
     belliger
    0.97
    পি
    0.93
    না
    0.89
     igneous
    0.88
    רים
    0.87
    ร
    0.87
    ي
    0.87
    Activations Density 0.002%

    No Known Activations