© 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. 205739
    Prev
    Next
    INDEX
    Explanations

    uss

    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
    BatchNorm
    0.41
     شبه
    0.37
     Alina
    0.37
    േന
    0.37
     شرح
    0.37
    юй
    0.37
    集合
    0.36
    赈
    0.36
    lblName
    0.35
    igts
    0.35
    POSITIVE LOGITS
     p
    1.34
     پ
    0.94
    p
    0.79
     п
    0.78
     प
    0.76
     P
    0.68
     פ
    0.66
     പ
    0.62
     ਪ
    0.62
     kitty
    0.62
    Activations Density 0.002%

    No Known Activations