© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137248
    Prev
    Next
    INDEX
    Explanations

    language barriers

    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
     Bax
    0.43
     ю
    0.43
     grammar
    0.41
     universe
    0.40
     uzys
    0.39
     nag
    0.38
     obtaining
    0.38
     IERC
    0.38
     баш
    0.37
     critiques
    0.37
    POSITIVE LOGITS
    練
    0.41
    ತಿಯ
    0.39
    ;'>
    0.39
     വിദ
    0.38
    বিট
    0.38
    面包
    0.37
    ಡೆಯ
    0.37
     profundizar
    0.36
    Practice
    0.36
     গভীর
    0.36
    Activations Density 0.007%

    No Known Activations