© 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. 1233
    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
    कारक
    1.72
    ل
    1.64
    র
    1.63
    ణు
    1.62
    р
    1.59
    naires
    1.56
    ن
    1.56
     έτσι
    1.51
    𝘴
    1.49
    ла
    1.49
    POSITIVE LOGITS
    yyyyyyyy
    1.62
     enforced
    1.53
    jším
    1.53
    tt
    1.52
    ffer
    1.51
     prescribed
    1.46
     diketahui
    1.45
    YYYY
    1.44
    cia
    1.43
    ROTTLE
    1.43
    Activations Density 0.058%

    No Known Activations