© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45746
    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_13_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
     პრო
    0.61
     వాటి
    0.59
     ৃ
    0.59
     젊
    0.55
     Want
    0.55
    🥅
    0.54
     ඒවා
    0.54
     සමඟ
    0.53
     દરેક
    0.53
    傆
    0.53
    POSITIVE LOGITS
    як
    0.61
    '
    0.60
    की
    0.57
    ryption
    0.52
    2
    0.52
    어
    0.51
    estados
    0.50
    я
    0.50
    气
    0.50
    نگ
    0.50
    Activations Density 0.000%

    No Known Activations