© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149844
    Prev
    Next
    INDEX
    Explanations

    list items or parentheses

    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_23_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
     komplette
    0.24
     Philosophical
    0.24
     toàn
    0.23
    鲷
    0.22
    లకు
    0.22
     স্বাধীন
    0.22
     interprets
    0.22
     AWD
    0.22
    सभी
    0.22
     Savings
    0.22
    POSITIVE LOGITS
    fontSize
    0.22
    sum
    0.21
     tempo
    0.21
    ళ
    0.20
    Cont
    0.19
     cont
    0.19
    times
    0.19
    Nest
    0.19
     اوقات
    0.19
    ኞች
    0.19
    Activations Density 0.012%

    No Known Activations