© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83315
    Prev
    Next
    INDEX
    Explanations

    der

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     बहादुर
    0.38
    生まれ
    0.38
    ^*_{
    0.37
     Tare
    0.36
    출
    0.36
    lendi
    0.35
    alg
    0.35
     ます
    0.35
     ら
    0.35
    ripsi
    0.35
    POSITIVE LOGITS
    ivate
    0.53
    ivad
    0.53
    iv
    0.52
    ivated
    0.52
    िव
    0.49
    Iv
    0.49
     iv
    0.47
    ivam
    0.47
    わた
    0.47
    IV
    0.47
    Activations Density 0.001%

    No Known Activations