© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37406
    Prev
    Next
    INDEX
    Explanations

    traffic stop and signals

    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
    от
    0.19
    También
    0.19
    ెస్
    0.18
    焲
    0.18
    ونک
    0.18
     мор
    0.18
    ammlung
    0.18
    Improve
    0.18
    èque
    0.18
     HDL
    0.17
    POSITIVE LOGITS
    )
    0.25
     dystopian
    0.18
    :
    0.18
    ;
    0.18
     about
    0.17
     award
    0.17
     lifetime
    0.17
    pallet
    0.17
    ள்ளது
    0.17
     termina
    0.17
    Activations Density 0.001%

    No Known Activations