© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11027
    Prev
    Next
    INDEX
    Explanations

    Mountain View locations

    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_13_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
    Ja
    0.55
    L
    0.53
    ூ
    0.53
    And
    0.50
    U
    0.50
    Me
    0.50
    J
    0.48
    وم
    0.47
    Indoor
    0.47
    Im
    0.46
    POSITIVE LOGITS
     constrain
    0.54
     banded
    0.53
     richieste
    0.52
     billion
    0.50
     billionaire
    0.50
     polymeric
    0.50
     druga
    0.50
    蹙
    0.50
     boomerang
    0.49
     padlock
    0.49
    Activations Density 0.003%

    No Known Activations