© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50717
    Prev
    Next
    INDEX
    Explanations

    custom items or features

    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
    StudentRecord
    0.38
     sofá
    0.38
     shutters
    0.38
    RewardedVideo
    0.38
    宿舍
    0.37
    道歉
    0.37
     uku
    0.37
    ⓐ
    0.37
    休闲
    0.37
     ആശയ
    0.37
    POSITIVE LOGITS
     toss
    0.41
    可靠
    0.40
    Reader
    0.37
     pilot
    0.37
     Dias
    0.37
     tossing
    0.37
     Reader
    0.37
     deus
    0.36
    君
    0.36
     reliability
    0.35
    Activations Density 0.059%

    No Known Activations