© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66954
    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_41_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
    ('-',
    0.38
     TTL
    0.38
    कार
    0.37
    住
    0.36
     enrichment
    0.35
     presentes
    0.35
    CAS
    0.34
    -+
    0.34
    म्ब
    0.34
     الطل
    0.34
    POSITIVE LOGITS
     discrimin
    0.48
    ogany
    0.44
    habi
    0.41
    redit
    0.38
     फिज
    0.38
     discriminate
    0.38
    яд
    0.38
     фут
    0.38
     Confidential
    0.36
     જાય
    0.36
    Activations Density 0.000%

    No Known Activations