© 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. 20571
    Prev
    Next
    INDEX
    Explanations

    expect

    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
    omyelitis
    0.41
    糕
    0.39
    IMO
    0.38
     በመ
    0.38
    РСР
    0.38
     DOB
    0.37
     टॉपर
    0.37
    стен
    0.36
    నో
    0.36
    샥
    0.36
    POSITIVE LOGITS
     {
    0.53
     expect
    0.44
     expects
    0.44
     Na
    0.41
     v
    0.39
     Expect
    0.39
     hizo
    0.38
    Expect
    0.38
     SOLUTION
    0.38
     scales
    0.37
    Activations Density 0.002%

    No Known Activations