© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193436
    Prev
    Next
    INDEX
    Explanations

    engine=InnoDB

    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_27_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
    റ
    0.41
     cards
    0.38
    )+"
    0.37
     MFP
    0.37
    ste
    0.37
    ্ডি
    0.37
    更
    0.37
    ва
    0.36
    ěru
    0.36
     RCB
    0.36
    POSITIVE LOGITS
     தயாரி
    0.43
    ContentLoaded
    0.42
    製品
    0.42
    眉头
    0.39
     TabLayout
    0.38
     бра
    0.38
     shortcomings
    0.38
     იმ
    0.36
     बारे
    0.36
     prejud
    0.36
    Activations Density 0.000%

    No Known Activations