© 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. 2483
    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
     referentes
    2.85
    وڑا
    2.69
     desempen
    2.68
    osw
    2.59
    ്
    2.57
     partir
    2.38
    für
    2.37
     ningún
    2.37
    젤
    2.34
     manc
    2.29
    POSITIVE LOGITS
     egregious
    2.91
     jeopardy
    2.75
     Newtown
    2.67
    𝒂
    2.60
    प्लीट
    2.59
    سال
    2.59
    izações
    2.59
    م
    2.50
     interchangeable
    2.48
     revenge
    2.47
    Activations Density 0.016%

    No Known Activations