© 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. 209907
    Prev
    Next
    INDEX
    Explanations

    first or second

    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
     совме
    0.21
    jde
    0.21
    ik
    0.20
    ill
    0.18
    /),
    0.18
    ck
    0.18
     hva
    0.18
    isko
    0.18
    ak
    0.17
    itt
    0.17
    POSITIVE LOGITS
    诞生
    0.20
     Helens
    0.20
     outskirts
    0.19
     hilly
    0.19
    树
    0.19
     ナイ
    0.19
     edific
    0.19
    誕生
    0.18
     watts
    0.18
     colors
    0.17
    Activations Density 0.001%

    No Known Activations