© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7063
    Prev
    Next
    INDEX
    Explanations

    file paths or case sensitivity

    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_40_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
    荫
    0.46
     Gateway
    0.43
     signature
    0.41
    ланы
    0.41
     gateway
    0.40
    signature
    0.39
     signatures
    0.39
     Signature
    0.39
    stroke
    0.36
     sillonné
    0.36
    POSITIVE LOGITS
     case
    0.48
    Case
    0.47
    ../
    0.46
     Case
    0.46
    README
    0.45
    :/
    0.44
    CASE
    0.43
     ../
    0.42
     عضو
    0.42
    ケース
    0.41
    Activations Density 0.071%

    No Known Activations