© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157247
    Prev
    Next
    INDEX
    Explanations

    position

    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_50_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
    Carr
    0.43
    ająca
    0.42
    ূল্যে
    0.41
    ającą
    0.40
     বপ
    0.39
     planters
    0.39
    planted
    0.38
    함
    0.37
    doch
    0.37
     déco
    0.36
    POSITIVE LOGITS
     Angular
    0.41
     Lor
    0.40
     mate
    0.39
     V
    0.38
     Vad
    0.38
     Mate
    0.38
     ஒன்றாகும்
    0.38
    Amer
    0.37
     dele
    0.36
     Latitude
    0.36
    Activations Density 0.000%

    No Known Activations