© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209616
    Prev
    Next
    INDEX
    Explanations

    significantly reduces

    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_25_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
    ೋಗ
    0.41
    ल्ल्या
    0.39
    Granted
    0.39
     수행
    0.39
     համար
    0.39
     beneficiary
    0.39
     člov
    0.38
    rania
    0.38
    倒
    0.38
    |-\
    0.37
    POSITIVE LOGITS
    也会
    0.41
     tambien
    0.40
     Gu
    0.38
    ین
    0.38
     Municip
    0.37
     Scop
    0.37
     También
    0.37
    也可以
    0.37
     Anche
    0.37
     Acest
    0.36
    Activations Density 0.008%

    No Known Activations