© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161199
    Prev
    Next
    INDEX
    Explanations

    language definition

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     aşağıdaki
    0.41
    上記の
    0.41
     શે
    0.38
    inaire
    0.38
     below
    0.37
     Below
    0.37
    以下
    0.36
    翌
    0.36
    )]=
    0.35
    茲
    0.35
    POSITIVE LOGITS
     overseen
    0.44
     gesprochen
    0.43
    APPROVED
    0.38
     presided
    0.37
     habla
    0.36
     parlato
    0.36
    Tiene
    0.36
     Oversight
    0.36
     Rides
    0.35
     Provided
    0.35
    Activations Density 0.000%

    No Known Activations