© 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. 167956
    Prev
    Next
    INDEX
    Explanations

    module declarations

    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
    动机
    0.44
     আৰ
    0.44
     Meanwhile
    0.44
    БУ
    0.40
    歸
    0.40
    Meanwhile
    0.38
    ColorF
    0.38
     दर्द
    0.37
    IONE
    0.37
    стойчи
    0.37
    POSITIVE LOGITS
     asterisk
    0.43
    滑
    0.39
    cep
    0.39
    cker
    0.38
     pouvoir
    0.37
     aster
    0.36
     practitioner
    0.36
    targets
    0.35
    makeText
    0.35
    pcm
    0.35
    Activations Density 0.000%

    No Known Activations