© 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. 2520
    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
     hou
    2.53
     morte
    2.48
    ین
    2.40
    де
    2.40
     racist
    2.30
    الع
    2.29
    ز
    2.26
    ყოფ
    2.23
     opnieuw
    2.19
    Unsupported
    2.18
    POSITIVE LOGITS
    其他
    3.17
     lname
    3.12
     случаях
    2.80
    ート
    2.64
     случаев
    2.63
    ()=>{
    2.60
    ্বস্ত
    2.57
     intents
    2.56
    रों
    2.55
    ayment
    2.55
    Activations Density 0.103%

    No Known Activations