© 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. 3176
    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
     그러니까
    1.25
    ్రి
    1.11
    Ľ
    1.08
    ্লা
    1.01
    á
    1.00
     szczególnie
    0.99
     poderá
    0.99
    乎
    0.99
    baar
    0.98
     pasal
    0.98
    POSITIVE LOGITS
    ب
    1.44
    ل
    1.22
    ли
    1.17
    empre
    1.15
    al
    1.14
    কেন্ড
    1.14
    ع
    1.12
    ści
    1.12
    ➋
    1.11
    
    1.08
    Activations Density 0.198%

    No Known Activations