© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2420
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    要
    1.09
    $$
    1.04
    {\
    1.03
    glazed
    1.02
    এর
    1.02
     পথে
    1.01
    resistant
    1.00
    &-
    1.00
    вых
    0.98
    स्था
    0.97
    POSITIVE LOGITS
     बारे
    1.25
     sheer
    1.17
    ン
    1.12
    न्न
    1.11
    sik
    1.09
    yte
    1.09
    Ꭹ
    1.09
    lı
    1.08
     mayhem
    1.06
     vicino
    1.06
    Activations Density 0.044%

    No Known Activations