© 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. 2522
    Prev
    Next
    INDEX
    Explanations

    Python code examples

    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
    ґ
    0.24
     stagger
    0.22
     зав
    0.22
     ach
    0.22
     сле
    0.22
     gew
    0.22
     ster
    0.21
     Abs
    0.21
     preciso
    0.21
     Kav
    0.21
    POSITIVE LOGITS
     местных
    0.25
    ''(
    0.24
    `](
    0.24
    '')
    0.24
     количеством
    0.23
    Política
    0.23
     собственных
    0.23
    CLI
    0.22
    nytimes
    0.22
    '',
    0.22
    Activations Density 3.214%

    No Known Activations