© 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. 209830
    Prev
    Next
    INDEX
    Explanations

    pod

    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
    ные
    1.11
    ires
    1.10
    리로
    1.02
    ного
    1.00
    ных
    1.00
     by
    0.99
    ု
    0.95
    ियों
    0.93
     При
    0.92
    </h2>
    0.91
    POSITIVE LOGITS
    d
    1.85
    ल
    1.58
    на
    1.44
    ন
    1.39
    ל
    1.39
    ul
    1.36
    de
    1.30
    st
    1.28
    n
    1.27
    र
    1.23
    Activations Density 0.002%

    No Known Activations