© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77505
    Prev
    Next
    INDEX
    Explanations

    four octets

    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_31_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
     가진
    0.38
    Karen
    0.38
     OXIDES
    0.38
     FORD
    0.38
     городе
    0.37
    眄
    0.36
     strengths
    0.36
    strength
    0.36
     отсутствии
    0.36
     Karen
    0.36
    POSITIVE LOGITS
    治安
    0.38
    尭
    0.37
     remains
    0.36
     syukur
    0.35
     компа
    0.34
     سنی
    0.34
    usahaan
    0.34
     دق
    0.34
     guidelines
    0.34
     integrated
    0.34
    Activations Density 0.007%

    No Known Activations