© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217532
    Prev
    Next
    INDEX
    Explanations

    geographical features

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     coastal
    1.45
    Coastal
    1.35
     Coastal
    1.34
     coast
    1.30
    海岸
    1.26
     coastline
    1.23
     উপকূল
    1.19
     Coast
    1.16
     ساح
    1.13
    岸
    1.12
    POSITIVE LOGITS
    ether
    0.37
     AMA
    0.36
     Spade
    0.35
     varphi
    0.35
    endum
    0.34
     Kart
    0.34
    heta
    0.34
     hydrol
    0.34
    唁
    0.34
    瞿
    0.34
    Activations Density 0.009%

    No Known Activations