© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179473
    Prev
    Next
    INDEX
    Explanations

    mid-level difficulty

    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
    closeup
    0.42
    现状
    0.39
     സൃഷ്ട
    0.37
    ര്‍ന്ന്
    0.37
    Bibliographie
    0.36
    𝓻
    0.36
     Сот
    0.35
     रूपये
    0.35
    萏
    0.35
    තුව
    0.35
    POSITIVE LOGITS
     universities
    0.40
     OpenAI
    0.36
     LL
    0.34
     health
    0.34
    0.33
     schools
    0.33
     relative
    0.33
     Relative
    0.33
     TV
    0.32
    পেক্ষ
    0.32
    Activations Density 0.019%

    No Known Activations