© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201686
    Prev
    Next
    INDEX
    Explanations

    things

    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
    бору
    0.41
    usega
    0.41
    мона
    0.39
     towed
    0.37
    蹟
    0.37
     lateinit
    0.37
     MinMaxScaler
    0.36
     খায়
    0.36
     chromatographed
    0.36
    stvu
    0.36
    POSITIVE LOGITS
     things
    0.58
     Things
    0.50
     THINGS
    0.46
    Things
    0.45
     coisas
    0.43
     cosas
    0.42
     вещей
    0.40
     thing
    0.39
     ગ્ર
    0.39
    것
    0.39
    Activations Density 0.004%

    No Known Activations