© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 131213
    Prev
    Next
    INDEX
    Explanations

    divine entities and abstract concepts

    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_25_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
     iconic
    0.39
     ro
    0.33
    움을
    0.33
     cornerstone
    0.33
    छ
    0.33
     ausführ
    0.32
     છો
    0.31
     mainland
    0.31
     biodegradable
    0.31
     elong
    0.31
    POSITIVE LOGITS
    EMAN
    0.41
    上帝
    0.39
    tach
    0.36
    ман
    0.35
     spirituality
    0.35
    ray
    0.33
    arness
    0.33
    耶稣
    0.33
    咎
    0.33
    ♾
    0.33
    Activations Density 0.023%

    No Known Activations