© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174060
    Prev
    Next
    INDEX
    Explanations

    leadership positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    ρα
    0.42
    park
    0.42
    riba
    0.42
    ιση
    0.40
    риб
    0.40
    adeva
    0.40
    肤
    0.39
    popup
    0.39
    РСР
    0.39
    llama
    0.39
    POSITIVE LOGITS
     condensers
    0.47
     fatalities
    0.47
     minifyEnabled
    0.46
    機会
    0.43
    ﻬ
    0.43
     தேர்த
    0.43
     distanciation
    0.42
     convicts
    0.42
    Westinghouse
    0.42
     meth
    0.41
    Activations Density 0.000%

    No Known Activations