© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36458
    Prev
    Next
    INDEX
    Explanations

    .each do

    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_11_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
     الفصل
    0.53
     =
    0.52
     но
    0.49
     राष्ट्रवादी
    0.48
    切れ
    0.48
    \}=
    0.48
     там
    0.48
     Colombian
    0.48
    使い方
    0.48
    诬
    0.48
    POSITIVE LOGITS
    D
    0.59
     diá
    0.55
     Elapsed
    0.53
    ات
    0.52
    ডিয়াম
    0.52
    oids
    0.51
    DPS
    0.50
     ${\
    0.50
    rit
    0.49
     $\
    0.49
    Activations Density 0.000%

    No Known Activations