© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 198553
    Prev
    Next
    INDEX
    Explanations

    literally above

    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_46_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
     التالي
    0.39
    丏
    0.37
     følgende
    0.36
    ຖ
    0.35
    uidos
    0.34
    ienia
    0.34
    ᅬ
    0.34
    ಷ್ಠ
    0.33
     खासा
    0.33
    笤
    0.31
    POSITIVE LOGITS
     above
    3.13
    above
    2.84
     выше
    2.77
    Above
    2.72
     Above
    2.66
    上述
    2.66
     acima
    2.58
    上記
    2.48
     aforementioned
    2.44
    上記の
    2.42
    Activations Density 0.001%

    No Known Activations