© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24321
    Prev
    Next
    INDEX
    Explanations

    innovative / innovation

    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_10_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
     on
    0.62
     $
    0.59
    Oil
    0.53
    ing
    0.46
     for
    0.46
     Oil
    0.46
     motel
    0.46
    ı
    0.46
    income
    0.45
    ä
    0.45
    POSITIVE LOGITS
    ométrique
    0.46
    ０
    0.45
    mét
    0.45
    sé
    0.45
    lated
    0.44
    daughters
    0.43
    ']->
    0.42
    積極
    0.42
    phe
    0.42
    räume
    0.41
    Activations Density 0.009%

    No Known Activations