© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173174
    Prev
    Next
    INDEX
    Explanations

    Google, Cisco, faster, up, increase

    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
    og
    0.55
     T
    0.49
    RestController
    0.46
    opl
    0.45
    ico
    0.44
    com
    0.44
    omu
    0.43
    aha
    0.42
    m
    0.41
     <
    0.41
    POSITIVE LOGITS
     ambientale
    0.44
    변경
    0.43
     sguardo
    0.43
    ష్య
    0.41
    溲
    0.41
     respiration
    0.41
     온도
    0.41
    нија
    0.40
     piv
    0.40
     evolución
    0.40
    Activations Density 0.000%

    No Known Activations