© 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. 6772
    Prev
    Next
    INDEX
    Explanations

    close connection

    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
     detection
    0.16
    lbrack
    0.15
     DETECTION
    0.15
     منسل
    0.15
     তহবিল
    0.14
     Detection
    0.14
    (−
    0.14
    𒋾
    0.13
    "،
    0.13
    BID
    0.13
    POSITIVE LOGITS
     closed
    0.23
    Closed
    0.21
    closed
    0.19
     closing
    0.18
    閉
    0.18
     закры
    0.18
     Closed
    0.17
    closing
    0.16
     closes
    0.16
    Closing
    0.16
    Activations Density 0.011%

    No Known Activations