© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100539
    Prev
    Next
    INDEX
    Explanations

    explaining reasons

    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_16_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
    сія
    0.52
    рія
    0.50
    ція
    0.46
     der
    0.45
    ллі
    0.45
    ร์
    0.44
    єю
    0.44
    є
    0.44
    ヤー
    0.43
     stammt
    0.43
    POSITIVE LOGITS
     adverts
    0.55
     insults
    0.54
    itivos
    0.53
     защита
    0.52
     lures
    0.52
     ushered
    0.51
     assaults
    0.50
     impedances
    0.50
     хозя
    0.50
     weeds
    0.49
    Activations Density 0.000%

    No Known Activations