© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41612
    Prev
    Next
    INDEX
    Explanations

    stagnant

    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_3_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
    at
    0.83
    زيد
    0.74
    0.71
    that
    0.71
    يت
    0.70
    ش
    0.68
    <0xBF>
    0.67
    ства
    0.66
     that
    0.65
     weave
    0.65
    POSITIVE LOGITS
     órganos
    0.79
    л
    0.77
     जाँच
    0.75
    プレス
    0.73
     تجزی
    0.72
     numerosos
    0.71
     judíos
    0.71
     ممالک
    0.70
    ornos
    0.69
     químicos
    0.69
    Activations Density 0.005%

    No Known Activations