© 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. 3362
    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
     entrusted
    2.04
     supprim
    1.88
    <bos>
    1.79
     rhy
    1.78
    ਂ
    1.77
    ון
    1.77
    łego
    1.69
     αφού
    1.69
    એ
    1.68
    炲
    1.68
    POSITIVE LOGITS
    ान
    1.96
    ️⃣
    1.90
    tained
    1.74
    halten
    1.73
    ⃣
    1.60
    standing
    1.58
    除此之外
    1.57
    美元
    1.52
    taining
    1.52
    yclerView
    1.48
    Activations Density 0.001%

    No Known Activations