© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214249
    Prev
    Next
    INDEX
    Explanations

    North Pole

    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_5_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
    1.31
    <0x0D>
    1.26
    ش
    1.02
    </h2>
    1.02
    这
    1.00
    ‬
    0.95
    </h6>
    0.94
    </h4>
    0.93
    </h3>
    0.90
    一边
    0.90
    POSITIVE LOGITS
    ла
    1.80
    in
    1.70
    at
    1.53
    ul
    1.51
    ar
    1.50
    as
    1.50
    ა
    1.48
    ia
    1.45
    ا
    1.39
    io
    1.37
    Activations Density 0.000%

    No Known Activations