© 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. 2256
    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
     loam
    1.76
    "\
    1.70
     большим
    1.63
     pathTo
    1.61
    <unused2148>
    1.60
    esian
    1.56
    ά
    1.53
    ்கள்
    1.52
     attested
    1.51
     adduct
    1.49
    POSITIVE LOGITS
    𝐢
    2.36
    𝐫
    2.21
    ानुसार
    2.12
    in
    2.06
    𝐛
    2.02
    𝐚
    1.97
    ل
    1.85
     acab
    1.75
    Д
    1.74
    ਡ
    1.73
    Activations Density 0.009%

    No Known Activations