© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 479
    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
    𝑒
    2.74
    ethyl
    2.70
    ম
    2.63
    ر
    2.57
    ar
    2.53
    <0x80>
    2.51
    𝑜
    2.49
    ěli
    2.48
     만큼
    2.48
    وين
    2.48
    POSITIVE LOGITS
     sinned
    2.53
    คง
    2.46
     불구하고
    2.39
    值
    2.33
    ไง
    2.29
    members
    2.25
     wages
    2.23
    情况
    2.14
    ك
    2.12
    ه
    2.10
    Activations Density 0.113%

    No Known Activations