© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112487
    Prev
    Next
    INDEX
    Explanations

    grâce à, graceful, race

    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_2_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
    '
    1.29
     on
    1.06
     mencion
    0.97
    the
    0.96
    dW
    0.95
    ”
    0.93
     coment
    0.90
     accue
    0.89
     réduit
    0.88
     consegu
    0.87
    POSITIVE LOGITS
    ات
    1.25
    </h3>
    1.19
    ↵
    1.18
    ك
    1.18
    ین
    1.10
    िंग
    1.07
    కు
    1.04
    <0x0D>
    1.02
    ני
    1.02
    ง
    1.01
    Activations Density 0.013%

    No Known Activations