© 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. 61981
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ;
    0.99
    thed
    0.91
    р
    0.88
    वत्ता
    0.85
     đế
    0.84
     Gaya
    0.81
    ل
    0.80
     нажа
    0.79
     ສຳ
    0.78
     météor
    0.77
    POSITIVE LOGITS
    as
    1.37
    ing
    1.28
    یت
    1.21
    ला
    1.14
    ેલ
    1.13
    p
    1.09
    it
    1.07
    "。
    1.07
     。
    1.06
    ด
    1.06
    Activations Density 0.000%

    No Known Activations