© 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. 2394
    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
    ми
    2.67
    fnamefont
    2.60
    ़
    2.59
     assorted
    2.40
    ि
    2.39
    স্ত
    2.39
     persoon
    2.33
    Misc
    2.33
    ти
    2.28
    ാ
    2.23
    POSITIVE LOGITS
    د
    3.51
    ন
    3.38
    न
    3.12
    да
    2.86
    வச
    2.85
    ও
    2.84
    EN
    2.72
    ۰
    2.65
    ব
    2.64
    М
    2.63
    Activations Density 0.010%

    No Known Activations