© 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. 230492
    Prev
    Next
    INDEX
    Explanations

    traffic cone and signs

    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
    सी
    1.23
    У
    1.23
    К
    1.13
    Он
    1.09
    ي
    1.09
    Т
    1.08
    И
    1.08
    Д
    1.02
    Мо
    1.02
    Си
    1.02
    POSITIVE LOGITS
    ä
    1.40
    ↵
    1.33
    \
    1.08
     US
    1.04
    ati
    1.02
     DIY
    1.00
    kl
    1.00
     U
    0.99
     W
    0.95
     Monday
    0.95
    Activations Density 0.000%

    No Known Activations