© 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. 208984
    Prev
    Next
    INDEX
    Explanations

    how it works:

    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
     отдельно
    0.42
    ()?
    0.42
     গার
    0.41
     safely
    0.39
     sneeze
    0.39
    ors
    0.39
    )*(
    0.39
    iiv
    0.39
     Sausage
    0.39
    Russian
    0.38
    POSITIVE LOGITS
     resultant
    0.43
    ývá
    0.42
     colaborador
    0.42
    Ф
    0.41
    П
    0.41
     ҷ
    0.40
    de
    0.39
     organismo
    0.39
     dia
    0.38
     कोण
    0.38
    Activations Density 0.007%

    No Known Activations