© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131222
    Prev
    Next
    INDEX
    Explanations

    supplies

    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_6_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
     have
    1.16
    я
    1.03
     an
    1.02
     HAVE
    1.01
     as
    0.98
    have
    0.98
     are
    0.95
    ة
    0.92
    ہ
    0.91
    ing
    0.90
    POSITIVE LOGITS
    ي
    1.41
    i
    1.23
    ри
    1.02
     Juegos
    0.98
    י
    0.96
    يرا
    0.94
    urando
    0.91
    ot
    0.89
     المك
    0.89
    وي
    0.89
    Activations Density 0.001%

    No Known Activations