© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33042
    Prev
    Next
    INDEX
    Explanations

    equality concepts

    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
     Async
    0.42
    astian
    0.40
    fst
    0.39
     dispensing
    0.38
     Wishes
    0.37
     dispense
    0.36
     есте
    0.36
    ໍ
    0.36
     Dyson
    0.36
    light
    0.35
    POSITIVE LOGITS
    Equal
    0.44
    TaskList
    0.44
     gelijk
    0.44
     Equal
    0.40
     égale
    0.39
     চ্যালেঞ্জ
    0.39
     observar
    0.39
    Thom
    0.38
     linearly
    0.38
    ريكي
    0.38
    Activations Density 0.000%

    No Known Activations