© 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. 2793
    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
     sempat
    1.70
    宾
    1.59
    賓
    1.54
    પૂર્ણ
    1.47
    वळ
    1.46
    cstdio
    1.44
     lige
    1.44
    chaften
    1.43
    aklar
    1.43
     fateful
    1.42
    POSITIVE LOGITS
    tional
    2.15
    tions
    1.88
    tion
    1.76
    ladesh
    1.65
    l
    1.60
    lly
    1.49
     =\
    1.47
     $^{
    1.46
    Closeup
    1.46
    cJ
    1.46
    Activations Density 0.126%

    No Known Activations