© 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. 139464
    Prev
    Next
    INDEX
    Explanations

    swallows whole, bottomless, wormhole, engine, observer

    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
     holes
    0.89
     hole
    0.84
     отверсти
    0.83
     Holes
    0.83
     Hole
    0.79
    穴
    0.75
    hole
    0.73
    holes
    0.72
     छेद
    0.59
    孔
    0.59
    POSITIVE LOGITS
     sn
    0.40
     animal
    0.39
     अराउंड
    0.38
     Mel
    0.38
    長的
    0.38
     Scre
    0.38
    зів
    0.38
     marg
    0.37
     observer
    0.36
    ឧប
    0.36
    Activations Density 0.036%

    No Known Activations