© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149203
    Prev
    Next
    INDEX
    Explanations

    the Buddha

    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_59_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
    ﾞ
    0.63
     vedit
    0.49
     dwa
    0.47
    মতো
    0.47
    winfx
    0.46
    ゙
    0.45
     rspace
    0.45
     വിദ്യാ
    0.43
     dwRes
    0.43
     MaterialApp
    0.42
    POSITIVE LOGITS
     p
    0.53
     سم
    0.53
     ק
    0.52
     카
    0.52
    𝑝
    0.52
    pling
    0.51
    카
    0.51
    サ
    0.51
     ص
    0.50
    ｐ
    0.50
    Activations Density 0.001%

    No Known Activations