© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44993
    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_22_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
     সৌমিত্র
    0.40
     Invoke
    0.39
    стные
    0.39
     fracture
    0.39
     chemist
    0.38
     предпо
    0.38
    训
    0.38
     интер
    0.37
    క్సి
    0.36
     belle
    0.36
    POSITIVE LOGITS
    contrad
    0.45
    麴
    0.41
     ಖ
    0.41
    all
    0.40
     ದು
    0.40
    āti
    0.39
    通话
    0.39
    અમ
    0.39
    Marathi
    0.39
    叒
    0.39
    Activations Density 0.000%

    No Known Activations