© 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. 3739
    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
    й
    3.93
     पड़ेगी
    2.84
     indi
    2.71
     اطلع
    2.68
    াত্য
    2.63
     embrace
    2.58
     例文帳に追加
    2.58
     дам
    2.55
    ダー
    2.47
    দ্ভুত
    2.46
    POSITIVE LOGITS
    ത്
    2.57
    on
    2.51
     ​​
    2.27
     fact
    2.24
    }");
    2.19
     verdad
    2.18
    tering
    2.16
    ेंगे
    2.16
    перь
    2.14
    '$
    2.14
    Activations Density 0.010%

    No Known Activations