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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139476
    Prev
    Next
    INDEX
    Explanations

    triggering signaling pathways

    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_37_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
     Hawaiian
    0.40
     colaborar
    0.39
    章
    0.38
    吠
    0.38
     obes
    0.38
     angst
    0.37
     catalyst
    0.36
     pain
    0.36
     tra
    0.35
     focus
    0.35
    POSITIVE LOGITS
    诮
    0.38
    copies
    0.38
     scavenging
    0.37
    ړئ
    0.37
    oría
    0.37
     surgery
    0.37
    ორ
    0.36
     പ്രസി
    0.36
    öre
    0.36
    ćen
    0.35
    Activations Density 0.001%

    No Known Activations