© 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. 233134
    Prev
    Next
    INDEX
    Explanations

    non-negotiable

    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
    Negative Logits
    ين
    1.36
    ك
    1.24
    م
    1.19
    ام
    1.16
    n
    1.13
    m
    1.09
    S
    1.09
    كان
    1.03
    de
    1.00
    تر
    1.00
    POSITIVE LOGITS
     і
    0.91
    '
    0.86
     breather
    0.82
    াই
    0.81
    LLER
    0.81
     forfeiture
    0.79
     persyaratan
    0.79
     foreclosure
    0.78
     accretion
    0.78
     oncologist
    0.77
    Activations Density 0.001%

    No Known Activations