© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108732
    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_1_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
     is
    1.35
     on
    1.27
     in
    1.13
    ل
    1.06
     acumen
    1.02
     et
    1.01
     evol
    1.00
     actors
    0.99
     descendants
    0.97
    อ
    0.97
    POSITIVE LOGITS
    <0x80>
    1.06
    il
    1.02
    Gestion
    1.01
    kowe
    0.92
     Viele
    0.91
    ádio
    0.91
    nahi
    0.91
    nél
    0.91
     نہيں
    0.90
    marshalN
    0.89
    Activations Density 0.000%

    No Known Activations