© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246934
    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_40_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
     cerr
    0.36
     tumble
    0.36
     |_{
    0.36
     Two
    0.35
    ଟ
    0.34
    chest
    0.34
    비스
    0.34
     viu
    0.33
    ข้อ
    0.33
     fuel
    0.33
    POSITIVE LOGITS
    динку
    0.42
    <0xBA>
    0.39
    frontend
    0.38
    ักษณะ
    0.37
    UIActions
    0.37
    ज्ञान
    0.37
    ಜ್ಞ
    0.37
    FileReader
    0.36
    নায়
    0.36
     Dialer
    0.36
    Activations Density 0.000%

    No Known Activations