© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    4. 178047
    Prev
    Next
    INDEX
    Explanations

    <

    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
    ဢ
    0.33
    ሀ
    0.33
    ें
    0.31
    另外
    0.30
    ရှ
    0.29
     ola
    0.29
     सहकारी
    0.29
    া
    0.29
    ाम
    0.28
    }$:
    0.28
    POSITIVE LOGITS
    桧
    0.34
    iculaire
    0.31
     `>=`,
    0.31
    acking
    0.30
    FlagSet
    0.30
     initializes
    0.29
    ляться
    0.29
     appending
    0.29
     rag
    0.29
     desta
    0.29
    Activations Density 0.006%

    No Known Activations