© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205761
    Prev
    Next
    INDEX
    Explanations

    0 or 1

    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
     presence
    0.46
     abnormally
    0.45
     présence
    0.42
     callers
    0.42
     bulletins
    0.40
     pregnant
    0.40
    ່ານ
    0.38
    Ꮠ
    0.38
     adaptarse
    0.38
    وه
    0.37
    POSITIVE LOGITS
    cr
    0.43
     Eucalyptus
    0.43
    tudo
    0.42
    sha
    0.42
    Vk
    0.42
    stanbul
    0.42
     Dependence
    0.42
    aires
    0.42
    autres
    0.42
     Av
    0.41
    Activations Density 0.008%

    No Known Activations