© 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. 67169
    Prev
    Next
    INDEX
    Explanations

    kites

    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
     K
    0.84
     kiosk
    0.80
     kink
    0.79
     k
    0.77
     kinks
    0.74
     kiosks
    0.73
    K
    0.66
     kines
    0.64
     ک
    0.61
     kios
    0.61
    POSITIVE LOGITS
    Ground
    0.46
     GROUND
    0.45
    ্রী
    0.45
     Ground
    0.45
     grounded
    0.43
     ground
    0.42
     suporte
    0.40
     поддержку
    0.39
     संभा
    0.39
    ground
    0.38
    Activations Density 0.001%

    No Known Activations