© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67374
    Prev
    Next
    INDEX
    Explanations

    immersion and submergence

    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_41_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
     pas
    0.39
     catch
    0.38
     WTA
    0.38
    カウン
    0.38
    💝
    0.38
     Siz
    0.36
     рези
    0.36
    galactos
    0.36
    ❤❤
    0.36
    薛
    0.36
    POSITIVE LOGITS
     immersion
    2.16
     immersed
    2.02
     immers
    1.98
     immerse
    1.94
     immersing
    1.91
     immersive
    1.69
     submerged
    1.68
     submer
    1.68
    immers
    1.64
     погру
    1.60
    Activations Density 0.098%

    No Known Activations