© 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. 206018
    Prev
    Next
    INDEX
    Explanations

    understanding [topic] structure

    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
     vignettes
    0.44
    ୋ
    0.41
     正
    0.41
    =","><
    0.40
     Poy
    0.40
     količ
    0.40
     宋
    0.40
     акты
    0.39
     acuity
    0.39
     GON
    0.38
    POSITIVE LOGITS
    ypso
    0.48
     daher
    0.46
    我们
    0.44
     você
    0.44
     Riders
    0.42
     nosso
    0.42
     нас
    0.41
    백
    0.40
    this
    0.40
     renvers
    0.40
    Activations Density 0.013%

    No Known Activations