© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193956
    Prev
    Next
    INDEX
    Explanations

    Boston University, police, Terriers, Dry Gin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
     on
    1.15
     of
    1.10
    '
    1.05
    2
    1.02
    اس
    0.93
    การ
    0.91
    \
    0.86
    et
    0.84
    ig
    0.84
    ست
    0.84
    POSITIVE LOGITS
     جوړونکو
    1.06
     جوړونک
    1.02
    ли
    1.01
     وړاندوینه
    1.01
    ﻼ
    1.00
     président
    0.99
    ো
    0.98
    لین
    0.97
    اکي
    0.97
     forgo
    0.97
    Activations Density 0.000%

    No Known Activations