© 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. 112281
    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
     was
    1.35
    ë
    1.29
    ING
    1.14
     Senate
    1.13
     District
    1.12
    ı
    1.12
     University
    1.08
    ü
    1.07
     Defense
    1.06
     September
    1.05
    POSITIVE LOGITS
    ᔾ
    1.45
     arenas
    1.29
     allemand
    1.27
     invariants
    1.26
     simplices
    1.24
     succulents
    1.24
     vacuoles
    1.23
     autochtones
    1.23
     échanc
    1.22
     égaux
    1.22
    Activations Density 0.000%

    No Known Activations