© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31919
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     अग
    0.40
    ಲೋ
    0.40
    बीसी
    0.39
    impul
    0.39
     নির্বাচ
    0.39
     அய
    0.39
     ক্ষেপ
    0.38
    닳
    0.38
    echen
    0.38
     Chine
    0.37
    POSITIVE LOGITS
     ন
    0.49
    anath
    0.49
    nat
    0.47
     nat
    0.46
     न
    0.45
     n
    0.44
     NAT
    0.44
     nath
    0.43
    نات
    0.43
    <0x98>
    0.42
    Activations Density 0.000%

    No Known Activations