© 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. 206388
    Prev
    Next
    INDEX
    Explanations

    asking questions about specific topics

    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
    barcode
    0.38
    Stop
    0.37
    header
    0.37
     Shutdown
    0.36
    aven
    0.36
    ሖ
    0.36
     liberated
    0.35
    Swim
    0.35
    龇
    0.35
     banderas
    0.35
    POSITIVE LOGITS
     jug
    0.41
     belong
    0.38
     stoj
    0.37
     ፕሮ
    0.37
     jugo
    0.36
    UMO
    0.36
     belongs
    0.36
     magicians
    0.36
     동안
    0.35
     saman
    0.35
    Activations Density 0.003%

    No Known Activations