© 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. 2021
    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
     Mathf
    2.23
    مان
    2.21
    <bos>
    2.15
    uments
    2.03
    о
    2.00
    rict
    1.98
    ্ম্ম
    1.97
    員
    1.95
    lasses
    1.92
    員の
    1.91
    POSITIVE LOGITS
    м
    2.87
    nên
    2.35
    ح
    2.32
     estan
    2.32
     Pact
    2.29
     dénom
    2.27
     són
    2.18
     discer
    2.18
     partir
    2.16
     automatis
    2.14
    Activations Density 0.060%

    No Known Activations