© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196957
    Prev
    Next
    INDEX
    Explanations

    some systems offer

    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_27_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
     선
    0.38
     Accountant
    0.30
     Corvette
    0.30
     восстанов
    0.30
     skeletal
    0.29
    ณฑ์
    0.29
     vandal
    0.28
     paddock
    0.28
     기
    0.28
     mediator
    0.28
    POSITIVE LOGITS
     Depending
    0.36
    Depending
    0.34
     terus
    0.33
     возможных
    0.33
    asi
    0.31
     ممكن
    0.31
    ของผู้
    0.31
    iq
    0.30
     déterminer
    0.30
    Hochspringen
    0.30
    Activations Density 0.004%

    No Known Activations