© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124139
    Prev
    Next
    INDEX
    Explanations

    LeetCode coding challenges

    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_37_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
    projectView
    0.41
     programmers
    0.41
    Programming
    0.40
     exámenes
    0.40
    鸮
    0.38
     programming
    0.38
     প্রোগ্রাম
    0.37
     プロ
    0.37
     અભ
    0.37
    鐟
    0.37
    POSITIVE LOGITS
     Garnier
    0.44
     matching
    0.38
    seen
    0.38
    panic
    0.38
    ˊ
    0.38
     arriv
    0.38
    Matching
    0.37
     spielen
    0.37
    ťa
    0.37
     matched
    0.36
    Activations Density 0.000%

    No Known Activations