© 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. 27258
    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
    ंदगी
    0.44
     меди
    0.43
     आपदा
    0.39
     meditations
    0.38
    Stabilise
    0.38
    㼛
    0.38
     замеча
    0.37
    観察
    0.37
     méd
    0.37
    翳
    0.37
    POSITIVE LOGITS
     उत्तीर्ण
    0.43
     salt
    0.41
     portraits
    0.39
     sach
    0.38
     Open
    0.38
     portrait
    0.38
     VN
    0.38
     existence
    0.38
    M
    0.37
     Salt
    0.37
    Activations Density 0.000%

    No Known Activations