© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8969
    Prev
    Next
    INDEX
    Explanations

    washes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     طریق
    1.58
    elem
    1.46
    ी
    1.42
     tackle
    1.41
    een
    1.36
    has
    1.36
    ../../
    1.33
    high
    1.27
    ối
    1.27
    much
    1.25
    POSITIVE LOGITS
    ра
    1.36
     Ease
    1.32
     cyclohex
    1.29
    𝚜
    1.29
     escuch
    1.21
    ℎ
    1.18
    ితో
    1.17
    𝑆
    1.16
    냠
    1.16
    ib
    1.15
    Activations Density 0.000%

    No Known Activations