© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139046
    Prev
    Next
    INDEX
    Explanations

    Bahrain

    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_37_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
     remittance
    0.44
     bn
    0.40
     Brion
    0.39
     ungdom
    0.38
     badminton
    0.38
     civic
    0.37
     Tobago
    0.37
     (+
    0.36
     maritime
    0.36
     utilising
    0.36
    POSITIVE LOGITS
     خر
    0.44
    omot
    0.42
    WCHAR
    0.41
     желез
    0.40
    荠
    0.40
    僞
    0.38
     Núñez
    0.37
     மிசோ
    0.37
     Nyl
    0.37
    殳
    0.37
    Activations Density 0.000%

    No Known Activations