© 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. 2261
    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
    ে
    1.20
    o
    1.12
    ம்
    1.04
    \{(
    1.01
     сми
    1.00
     shutout
    0.99
    داران
    0.99
    ação
    0.98
    ுக்கு
    0.95
    \{
    0.93
    POSITIVE LOGITS
    ла
    1.12
    NF
    1.12
     bela
    1.08
    éder
    1.04
    voll
    1.04
    CK
    1.03
    inin
    1.03
    లోని
    1.00
    হান
    0.99
     palp
    0.99
    Activations Density 0.285%

    No Known Activations