© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79431
    Prev
    Next
    INDEX
    Explanations

    powerful / sprinter / Allie

    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_0_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
    t
    2.44
    d
    1.79
     for
    1.65
    tä
    1.39
    m
    1.34
    st
    1.34
    ts
    1.32
    time
    1.30
    test
    1.27
    timer
    1.27
    POSITIVE LOGITS
    ير
    1.84
    </strong>
    1.63
    是
    1.62
    은
    1.61
    ના
    1.59
    は
    1.55
    ני
    1.51
    س
    1.50
    </h5>
    1.45
    </b>
    1.45
    Activations Density 0.000%

    No Known Activations