© 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. 3675
    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
    ות
    1.45
    ان
    1.30
    ve
    1.29
    ছিলেন
    1.28
    তে
    1.27
    й
    1.23
    ো
    1.19
    ून
    1.17
    ))$,
    1.16
    els
    1.13
    POSITIVE LOGITS
    pyrimidine
    1.63
    aac
    1.51
     sphinct
    1.47
    thirds
    1.46
    不錯
    1.46
    ल
    1.44
     jazdy
    1.44
     arteri
    1.42
    পূর্ণ
    1.42
     énon
    1.40
    Activations Density 0.017%

    No Known Activations