© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112140
    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_2_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
    
    1.22
     incisions
    1.20
     in
    1.14
    ்ப
    1.12
     instabilities
    1.12
    在
    1.06
     inhomogeneities
    1.03
     inodes
    1.02
    \
    1.02
    𝓑
    1.00
    POSITIVE LOGITS
    ية
    1.64
     has
    1.48
    、
    1.38
    де
    1.38
     be
    1.35
     have
    1.34
    -
    1.34
     is
    1.25
     heeft
    1.18
    ，
    1.12
    Activations Density 0.000%

    No Known Activations