© 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. 2490
    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
    ي
    1.74
    ע
    1.59
    ్యాచ్
    1.57
    ات
    1.56
    dehyde
    1.54
     decedent
    1.52
    dancer
    1.52
    malign
    1.48
     inadvert
    1.47
     chiefs
    1.47
    POSITIVE LOGITS
    𝙡
    1.89
     Semaphore
    1.68
    𝙀
    1.68
    𝙧
    1.66
    𝐼
    1.66
    𝐸
    1.65
    ا
    1.63
    munk
    1.63
    𝑀
    1.61
    ͢
    1.61
    Activations Density 0.001%

    No Known Activations