© 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. 5941
    Prev
    Next
    INDEX
    Explanations

    memory overhead

    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
    Shared
    0.44
     shared
    0.44
    shared
    0.44
    allaitement
    0.42
     condiv
    0.42
    SHARED
    0.41
     synced
    0.38
    夊
    0.37
     Shared
    0.37
     compartido
    0.37
    POSITIVE LOGITS
     roots
    0.46
     Roots
    0.43
     root
    0.43
    ร่างกาย
    0.42
     mode
    0.41
    モード
    0.41
     Directory
    0.41
    vues
    0.40
    mark
    0.39
     scam
    0.39
    Activations Density 0.081%

    No Known Activations