© 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. 9186
    Prev
    Next
    INDEX
    Explanations

    romanze, Nadal, poem

    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
    с
    0.55
    çe
    0.48
    вими
    0.45
    𝐞
    0.45
     advent
    0.44
     वर्गी
    0.44
     pew
    0.44
    د
    0.43
    ート
    0.43
    >
    0.43
    POSITIVE LOGITS
    hny
    0.55
    netstandard
    0.53
    től
    0.50
    elem
    0.50
    ই
    0.49
    ről
    0.48
    hype
    0.47
    िशनर
    0.47
    nej
    0.46
    precio
    0.46
    Activations Density 0.003%

    No Known Activations