© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207940
    Prev
    Next
    INDEX
    Explanations

    eyes and what follows

    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
    kę
    0.24
     bør
    0.24
     hvad
    0.24
     सर
    0.23
    脸
    0.23
     détente
    0.22
     jīn
    0.22
     Kangaroo
    0.22
    🌵
    0.22
     wú
    0.22
    POSITIVE LOGITS
    Ста
    0.25
     syscall
    0.25
    Полу
    0.23
    point
    0.22
    nucle
    0.22
    Sodium
    0.22
     Zeitpunkt
    0.22
    Референ
    0.22
    deploy
    0.22
    andolo
    0.22
    Activations Density 0.004%

    No Known Activations