© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39053
    Prev
    Next
    INDEX
    Explanations

    regex start of line `^`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    ↵
    0.68
     gesam
    0.56
    '
    0.55
     func
    0.54
     civil
    0.54
     plot
    0.53
     exposure
    0.53
     oversight
    0.53
     situation
    0.52
     snow
    0.51
    POSITIVE LOGITS
    degenerate
    0.68
     遅く
    0.64
    illerie
    0.60
    arrayList
    0.59
     而且
    0.59
     університету
    0.59
    亍
    0.58
     বেঙ্গল
    0.57
    nBitCount
    0.57
     Questi
    0.56
    Activations Density 0.041%

    No Known Activations