© 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. 2815
    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
    ெ
    2.98
    р
    2.87
    గు
    2.84
     φορά
    2.80
    랫폼
    2.66
     enduring
    2.61
    ب
    2.60
     broom
    2.58
    во
    2.49
    ्रो
    2.48
    POSITIVE LOGITS
    es
    3.25
    ez
    3.17
    eing
    2.89
    euler
    2.86
    ed
    2.79
    Measuring
    2.62
    ei
    2.61
    tfidf
    2.56
    Πα
    2.55
    𝚜
    2.55
    Activations Density 0.001%

    No Known Activations