© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233272
    Prev
    Next
    INDEX
    Explanations

    Handling loading

    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_46_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
     blow
    0.57
    Blow
    0.49
     driving
    0.48
    Drive
    0.46
    Driving
    0.45
    吹
    0.45
    driving
    0.44
     drives
    0.43
     Blow
    0.43
     blown
    0.41
    POSITIVE LOGITS
    载
    0.47
     Handling
    0.46
     handled
    0.44
     HANDLING
    0.41
     نب
    0.41
     handling
    0.40
    gé
    0.39
     Loading
    0.38
     කර
    0.38
     Lub
    0.38
    Activations Density 0.000%

    No Known Activations