© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1466
    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
    ১৯
    1.83
    ので
    1.66
    ⺈
    1.61
    究竟
    1.58
    亠
    1.56
     NSDictionary
    1.53
     translateY
    1.53
     hygienic
    1.52
    lık
    1.51
    ̈́
    1.49
    POSITIVE LOGITS
    et
    3.11
    etar
    2.37
    en
    2.21
    𝒅
    2.08
    𝒏
    2.01
    ed
    2.00
    kend
    1.88
    es
    1.87
    quantidade
    1.87
     dextrose
    1.87
    Activations Density 0.090%

    No Known Activations