© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7316
    Prev
    Next
    INDEX
    Explanations

    UI component names

    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_40_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
     yüks
    0.34
     تعین
    0.33
     नैसर्गिक
    0.33
    鲷
    0.33
     ers
    0.32
     returnMe
    0.32
    िरपेक्ष
    0.32
    摻
    0.32
    ulitan
    0.31
     ½
    0.31
    POSITIVE LOGITS
     suspending
    0.38
     suspended
    0.36
    OP
    0.36
    PathResource
    0.36
     suspensions
    0.35
    Susp
    0.34
     suspension
    0.34
    libro
    0.33
    suspended
    0.33
     suspend
    0.32
    Activations Density 0.001%

    No Known Activations