© 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. 4023
    Prev
    Next
    INDEX
    Explanations

    Log data identifiers

    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
    glBind
    0.23
    żeli
    0.23
    ﭥ
    0.23
     gradi
    0.23
     Faz
    0.23
    室内
    0.22
    瓯
    0.22
     phase
    0.22
     institute
    0.22
    尹
    0.22
    POSITIVE LOGITS
     Literal
    0.22
     Mustache
    0.21
    тр
    0.21
    個人
    0.21
    personal
    0.21
     foco
    0.21
    кугӀ
    0.21
     Baca
    0.20
    ahrer
    0.20
    ্য
    0.20
    Activations Density 0.001%

    No Known Activations