© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61751
    Prev
    Next
    INDEX
    Explanations

    winston

    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_2_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
     synthes
    1.16
     reorgan
    1.16
     pressur
    1.14
     appet
    1.09
     synchron
    1.08
    w
    1.04
     renormal
    0.98
     hypothes
    0.97
     categor
    0.95
    xiety
    0.94
    POSITIVE LOGITS
    ي
    1.58
    ו
    1.47
    ли
    1.41
    '
    1.28
    ק
    1.27
    تين
    1.26
    اني
    1.23
    دين
    1.15
    ري
    1.14
    。
    1.10
    Activations Density 0.000%

    No Known Activations