© 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. 107810
    Prev
    Next
    INDEX
    Explanations

    tsuyu (rainy season)

    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
    า
    1.55
    ী
    1.50
    to
    1.46
    '
    1.45
    ı
    1.45
    та
    1.23
    that
    1.21
    H
    1.20
    li
    1.19
    i
    1.19
    POSITIVE LOGITS
    h
    1.34
    ق
    1.00
     configur
    0.98
     contrat
    0.96
     contribu
    0.95
     do
    0.93
     detour
    0.93
    éc
    0.92
     have
    0.91
     refriger
    0.90
    Activations Density 0.007%

    No Known Activations