© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154195
    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_23_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
     calcium
    0.47
     grassy
    0.46
    Kc
    0.42
     sunny
    0.42
     fluor
    0.42
     branca
    0.41
     sund
    0.40
     d
    0.40
    щую
    0.40
     ష
    0.39
    POSITIVE LOGITS
     یونیورسٹی
    0.48
     نئی
    0.44
    ayak
    0.42
     ವಿಷಯ
    0.42
    ismillahirrah
    0.41
     سسٹم
    0.41
     університе
    0.40
    াইজ
    0.40
     Entomology
    0.38
     پاورپوینت
    0.38
    Activations Density 0.000%

    No Known Activations