© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206839
    Prev
    Next
    INDEX
    Explanations

    actions or states

    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_20_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
     আরে
    0.43
    雨
    0.43
     рекорд
    0.42
     Algunos
    0.40
    库
    0.39
    领域
    0.39
    山田
    0.38
     高
    0.38
     رج
    0.38
     레
    0.38
    POSITIVE LOGITS
    \},\{
    0.48
     lenght
    0.48
     loops
    0.48
     Coroner
    0.47
     ludzi
    0.47
     Loops
    0.47
     cranks
    0.46
     exo
    0.46
     kori
    0.46
     chaleur
    0.45
    Activations Density 0.012%

    No Known Activations