© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256842
    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_10_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
    ties
    1.37
    ted
    1.17
    ting
    1.17
     الفاظ
    1.13
    mselves
    1.13
    self
    1.08
    t
    1.04
    tions
    1.04
    %{
    1.03
    ts
    1.00
    POSITIVE LOGITS
     épais
    1.36
     permettent
    1.35
     bellissimo
    1.33
     retour
    1.33
    ढ़े
    1.33
     essentiellement
    1.26
    杯
    1.25
     jeunes
    1.24
     aurez
    1.24
     tiempo
    1.24
    Activations Density 0.000%

    No Known Activations