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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51561
    Prev
    Next
    INDEX
    Explanations

    date context

    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_30_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
    Narrow
    0.27
    过去
    0.25
     Narrow
    0.25
    订单
    0.24
    狭
    0.24
     narrower
    0.24
    崩溃
    0.23
    ariyati
    0.23
    White
    0.23
     sneaking
    0.23
    POSITIVE LOGITS
     Gewinn
    0.29
     haies
    0.29
     augmente
    0.28
     remport
    0.28
     arent
    0.28
     ಅಥವಾ
    0.27
     വാർത്ത
    0.27
    庤
    0.27
    atual
    0.27
    리는
    0.26
    Activations Density 0.000%

    No Known Activations