© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79196
    Prev
    Next
    INDEX
    Explanations

    net

    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_53_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
     Kraft
    0.54
    kraft
    0.47
    Kraft
    0.46
     kraft
    0.44
     Gest
    0.44
     मं
    0.42
    權
    0.42
    Gest
    0.41
     w
    0.41
    権
    0.41
    POSITIVE LOGITS
     net
    0.97
     nets
    0.95
     Net
    0.93
    Net
    0.89
     Netz
    0.84
     NET
    0.80
     নেট
    0.80
     नेट
    0.79
     Nets
    0.79
    net
    0.78
    Activations Density 0.020%

    No Known Activations