© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250149
    Prev
    Next
    INDEX
    Explanations

    general

    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_56_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
     l
    1.13
     ल
    0.66
    ล
    0.65
     ل
    0.63
     л
    0.60
    ｌ
    0.57
     લ
    0.55
    l
    0.51
     L
    0.48
    л
    0.46
    POSITIVE LOGITS
     general
    0.53
    general
    0.51
     général
    0.49
    General
    0.48
     General
    0.48
     deb
    0.40
    GENERAL
    0.40
     simplicial
    0.40
     Lieben
    0.40
     continuación
    0.39
    Activations Density 0.003%

    No Known Activations