© 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. 225199
    Prev
    Next
    INDEX
    Explanations

    paid for services or actions

    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
     C
    0.29
    ación
    0.29
     loses
    0.29
     eosin
    0.29
     can
    0.28
     अधिक
    0.27
     азо
    0.27
     antimicrobial
    0.26
     células
    0.26
     spines
    0.26
    POSITIVE LOGITS
    d
    0.38
    the
    0.31
    ೆಯಿಂದ
    0.31
    t
    0.31
    $.}
    0.30
    ى
    0.30
    }\\
    0.29
    ئیں۔
    0.29
    }.
    0.29
    جات
    0.29
    Activations Density 0.004%

    No Known Activations