© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120186
    Prev
    Next
    INDEX
    Explanations

    episodes, seasons, books, games

    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_27_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
    ju
    0.35
     legitimately
    0.35
    യ്ക്ക
    0.35
    policies
    0.33
     호
    0.33
    ujući
    0.33
     pessimism
    0.32
     interfaces
    0.32
     negativity
    0.32
     simply
    0.31
    POSITIVE LOGITS
    Concat
    0.37
    ទ្ធ
    0.36
    Enh
    0.35
    啉
    0.34
     Byrne
    0.33
     далее
    0.33
    Enhanced
    0.33
     genü
    0.32
     п
    0.32
     новые
    0.32
    Activations Density 0.003%

    No Known Activations