© 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-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18790
    Prev
    Next
    INDEX
    Explanations

    loop variables and increments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_width_262k_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
    昔
    0.38
    ொட
    0.36
     Miss
    0.35
    invasive
    0.34
     unfolding
    0.34
    Fantastic
    0.34
    awat
    0.33
    createComponent
    0.33
     DM
    0.33
     Passive
    0.33
    POSITIVE LOGITS
     entrambe
    0.38
    ruta
    0.38
     lymphoma
    0.37
     Lotion
    0.37
    枞
    0.36
    𝐤
    0.36
     liberar
    0.35
     ню
    0.35
    ClkInitStruct
    0.35
    混合
    0.35
    Activations Density 0.004%

    No Known Activations