© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164741
    Prev
    Next
    INDEX
    Explanations

    нет одного, есть ли

    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_31_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
     wspom
    0.36
     comenta
    0.36
    묽
    0.36
     Sekunden
    0.36
     Eventually
    0.35
     drewn
    0.35
     sa
    0.34
    qualiter
    0.34
     انھوں
    0.34
     컨트롤
    0.34
    POSITIVE LOGITS
     ipc
    0.33
     inhabited
    0.32
     borders
    0.32
     сум
    0.31
     tensione
    0.31
    icio
    0.31
    Backward
    0.31
    宵
    0.30
    UTC
    0.29
    Diagonal
    0.29
    Activations Density 0.000%

    No Known Activations