© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232866
    Prev
    Next
    INDEX
    Explanations

    tackle

    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_6_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
    0
    1.05
    ’
    1.02
    。
    1.02
     \
    0.91
    ۔
    0.88
    {
    0.87
     inputRange
    0.84
     maksymal
    0.84
    }
    0.84
     linkCell
    0.84
    POSITIVE LOGITS
    ן
    1.38
    ет
    1.28
    й
    1.20
    지
    1.20
    та
    1.19
     be
    1.09
    ή
    1.07
    ных
    1.06
    م
    1.06
    ει
    1.05
    Activations Density 0.000%

    No Known Activations