© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10304
    Prev
    Next
    INDEX
    Explanations

    Khan Academy and URLs

    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
     Endpoint
    0.43
     சக
    0.42
     idling
    0.40
    第一百
    0.38
     지방
    0.37
    TRAN
    0.36
     Gert
    0.36
    橫
    0.36
     پڑھیئے
    0.36
     విశ్వ
    0.36
    POSITIVE LOGITS
    approche
    0.42
    Nine
    0.40
    India
    0.39
    uillez
    0.38
    Kotlin
    0.38
    ണ്ടി
    0.38
    Ɩ
    0.38
     buzz
    0.37
    BN
    0.37
    ATIVE
    0.37
    Activations Density 0.030%

    No Known Activations