© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28488
    Prev
    Next
    INDEX
    Explanations

    drone swarm, hive, Docker

    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_40_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
    凹
    0.41
    んな
    0.38
     angolo
    0.37
    തിനാ
    0.37
    途
    0.36
     поло
    0.35
     Fatty
    0.35
    朳
    0.35
     Garfield
    0.34
     ابن
    0.34
    POSITIVE LOGITS
     swarm
    2.08
    swarm
    1.77
     Sw
    1.68
     sw
    1.59
    Sw
    1.58
    sw
    1.23
     hive
    1.19
     Hive
    1.03
    hive
    1.01
     SW
    0.96
    Activations Density 0.111%

    No Known Activations