© 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. 3583
    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
     breezes
    2.53
    泞
    2.49
     പ്രത്യേ
    2.48
    $),
    2.45
    一夜
    2.42
    ्रेडिट
    2.39
    চ্ছু
    2.34
    ʰ
    2.33
    Prosecutors
    2.31
    lemen
    2.31
    POSITIVE LOGITS
    en
    3.00
    માં
    2.94
     cuales
    2.58
    de
    2.54
    те
    2.45
    ству
    2.40
    క
    2.37
    렬
    2.36
    gado
    2.34
     aids
    2.33
    Activations Density 0.029%

    No Known Activations