© 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. 3685
    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
    r
    1.76
     textColor
    1.55
     Carefully
    1.52
    ن
    1.51
    ۰
    1.47
    nahme
    1.43
    _{\
    1.43
    ानुसार
    1.41
    ل
    1.38
    ные
    1.36
    POSITIVE LOGITS
     koht
    1.59
    ीकरण
    1.54
     hver
    1.49
    電源
    1.47
    elligence
    1.46
     yaar
    1.44
     pintu
    1.43
     brunâtre
    1.43
    accord
    1.39
    тріш
    1.39
    Activations Density 0.013%

    No Known Activations