© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 168062
    Prev
    Next
    INDEX
    Explanations

    the

    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
     /
    0.41
    this
    0.39
     \%)$,
    0.39
     main
    0.38
     desired
    0.38
    desired
    0.38
    adores
    0.38
    columns
    0.38
     Objective
    0.37
    这位
    0.36
    POSITIVE LOGITS
     odds
    0.51
     Tatsache
    0.50
     driving
    0.45
     fact
    0.44
    杮
    0.44
     prospect
    0.42
    driving
    0.42
     Odds
    0.41
     revival
    0.39
    گم
    0.39
    Activations Density 0.003%

    No Known Activations