© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54648
    Prev
    Next
    INDEX
    Explanations

    over [number]

    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_30_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
    ActionButton
    0.20
    鋐
    0.19
    خب
    0.18
    urator
    0.18
    ങ്ങ്
    0.17
     خوف
    0.17
    باشد
    0.17
     ಹೋಗ
    0.16
     कोणते
    0.16
    major
    0.16
    POSITIVE LOGITS
    riages
    0.20
    ৩৫
    0.19
     другими
    0.17
     younger
    0.17
     Danes
    0.16
     jovens
    0.16
    障
    0.16
     demonstr
    0.16
     канализа
    0.16
     Cambridge
    0.16
    Activations Density 0.003%

    No Known Activations