© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177721
    Prev
    Next
    INDEX
    Explanations

    投入后 xxx 基础

    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_24_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
     nucle
    0.46
     kinks
    0.43
    nummer
    0.42
    Ճ
    0.40
     pescado
    0.40
    setNome
    0.40
     marco
    0.39
     camshaft
    0.38
     carre
    0.38
    ilgan
    0.38
    POSITIVE LOGITS
     Uyg
    0.42
    ্যা
    0.41
     Stat
    0.40
     Turf
    0.40
     Ев
    0.39
     Buildings
    0.38
    湎
    0.36
    Stat
    0.36
     地
    0.36
    owners
    0.35
    Activations Density 0.001%

    No Known Activations