© 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. 3697
    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
    ীয়
    1.79
     monolayers
    1.63
    로
    1.51
     coffers
    1.48
    tonic
    1.46
     любят
    1.45
     Recherches
    1.45
    та
    1.44
    ীয়
    1.42
    ک
    1.42
    POSITIVE LOGITS
    ment
    1.38
    ٍ
    1.34
    ار
    1.33
    lah
    1.31
    ociação
    1.27
    hood
    1.26
     начало
    1.26
     insulator
    1.26
    asd
    1.23
    𝘀
    1.22
    Activations Density 0.394%

    No Known Activations