© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 33719
    Prev
    Next
    INDEX
    Explanations

    say "step"

    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
     stepping
    1.02
    stepping
    0.95
     stepped
    0.67
    踏
    0.63
     Steps
    0.53
     stepper
    0.52
    Steps
    0.52
    steps
    0.49
    STEP
    0.49
    Stepper
    0.49
    POSITIVE LOGITS
    ત્રો
    0.36
    ansi
    0.36
     quiera
    0.36
    dns
    0.35
    evi
    0.35
    SetStr
    0.34
     ਅ
    0.33
     ol
    0.32
    ea
    0.32
     보이
    0.32
    Activations Density 0.013%

    No Known Activations