© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199791
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     mu
    0.47
     му
    0.43
    mu
    0.41
    FBSDKAccessToken
    0.40
    раз
    0.38
     mv
    0.38
     نیاز
    0.38
    滗
    0.37
     Михай
    0.37
    DA
    0.36
    POSITIVE LOGITS
    twig
    0.43
     ट्व
    0.42
    ezers
    0.40
    ሮች
    0.40
    ISTICS
    0.39
     Realistic
    0.38
    Realistic
    0.38
     inconsistencies
    0.38
    minim
    0.38
    grounds
    0.37
    Activations Density 0.001%

    No Known Activations