© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 9009
    Prev
    Next
    INDEX
    Explanations

    perception of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    gm
    1.49
    Notwithstanding
    1.33
    েজ
    1.33
     पासवान
    1.33
    deutscher
    1.31
    payroll
    1.28
    濘
    1.27
    ㅀ
    1.23
    これで
    1.22
    gli
    1.21
    POSITIVE LOGITS
    ️⃣
    1.52
    ত
    1.48
    на
    1.39
     focal
    1.35
    Ӏо
    1.31
    >)</
    1.31
    ството
    1.31
    न्देल
    1.29
    𝑇
    1.27
    ુ
    1.26
    Activations Density 0.075%

    No Known Activations