© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54388
    Prev
    Next
    INDEX
    Explanations

    python package installations

    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_31_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
     Bl
    0.27
    Teaching
    0.26
     cadáver
    0.26
    ॲ
    0.26
    DLE
    0.25
    USA
    0.25
     ಅರ್ಥ
    0.25
     TBA
    0.24
     하는데
    0.24
     Teaching
    0.24
    POSITIVE LOGITS
     Lili
    0.28
    ວ່າ
    0.26
    堅
    0.26
     அலு
    0.25
    衆
    0.25
     monochrome
    0.25
     tread
    0.25
    compile
    0.25
    âns
    0.24
    }}}+\
    0.24
    Activations Density 0.010%

    No Known Activations