© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157492
    Prev
    Next
    INDEX
    Explanations

    Andre

    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_50_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
     PI
    0.47
    പി
    0.43
    PI
    0.42
     сх
    0.41
     xaxis
    0.41
    松
    0.41
     Bae
    0.40
    uner
    0.39
     ખ્ર
    0.38
     భ
    0.37
    POSITIVE LOGITS
     Andre
    0.55
    Andre
    0.53
     Igu
    0.53
     bar
    0.50
     IG
    0.46
     ignor
    0.46
     बार
    0.45
     André
    0.45
     igu
    0.45
     Ig
    0.45
    Activations Density 0.005%

    No Known Activations