© 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. 3803
    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
    ва
    2.30
     collisional
    2.28
    狠狠
    2.24
     lắp
    2.18
     finer
    2.14
    Introducing
    2.12
    斛
    2.12
    दरअसल
    2.09
    Ç
    2.09
     apoptosis
    2.08
    POSITIVE LOGITS
    ী
    2.61
    ًا
    2.53
     bores
    2.38
     फिर
    2.28
    alanine
    2.24
    𝘆
    2.24
     सिलसिला
    2.24
    !\!\
    2.23
     काल
    2.22
    情况下
    2.21
    Activations Density 0.035%

    No Known Activations