© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208885
    Prev
    Next
    INDEX
    Explanations

    object storage

    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_20_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
     drops
    0.47
     Rue
    0.44
     Drops
    0.43
     Amanda
    0.43
     Selamat
    0.40
     d
    0.40
     könny
    0.40
    向
    0.39
     Allocate
    0.39
    CONT
    0.38
    POSITIVE LOGITS
    пад
    0.44
     scholarly
    0.43
    მასრულ
    0.42
     prayed
    0.42
     scrutinized
    0.42
     zamknię
    0.41
    fdPar
    0.40
    dropPanel
    0.40
     ير
    0.40
    studentRecord
    0.40
    Activations Density 0.002%

    No Known Activations