© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129620
    Prev
    Next
    INDEX
    Explanations

    mathematics and analysis

    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_1_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
    ب
    1.27
    ة
    1.14
    isations
    1.09
    ains
    1.01
    }];
    0.98
    arbeiter
    0.97
     that
    0.93
    ى
    0.93
    }";
    0.93
    ل
    0.93
    POSITIVE LOGITS
    с
    1.43
    ра
    1.27
    کر
    1.27
    ssä
    1.27
    го
    1.24
     moistur
    1.20
     government
    1.11
     trong
    1.11
    اک
    1.08
     į
    1.08
    Activations Density 0.000%

    No Known Activations