© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199592
    Prev
    Next
    INDEX
    Explanations

    return or run

    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_27_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
    urang
    0.44
    ابية
    0.40
     hydrating
    0.39
    趵
    0.39
     designates
    0.39
     sabah
    0.37
     wade
    0.37
     جارہ
    0.37
     wading
    0.35
     hears
    0.35
    POSITIVE LOGITS
     Hover
    0.40
    箭
    0.37
     الحصول
    0.36
     REPLACE
    0.36
     प्रौ
    0.36
    VAR
    0.35
     सोचते
    0.35
     معاش
    0.35
    技術
    0.35
     Hinweise
    0.34
    Activations Density 0.000%

    No Known Activations