© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31808
    Prev
    Next
    INDEX
    Explanations

    fluid accumulation or buildup

    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_31_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
     amphithe
    0.42
    AMENTO
    0.41
    appartement
    0.36
    輛
    0.36
     samoglas
    0.35
     armada
    0.35
     backs
    0.35
    OTC
    0.35
     완전히
    0.35
     alde
    0.34
    POSITIVE LOGITS
     Пи
    0.37
    clid
    0.36
    zków
    0.35
     Caring
    0.35
     Prefer
    0.34
    営
    0.34
     Phot
    0.34
     تمر
    0.34
     Prit
    0.33
     Seeger
    0.33
    Activations Density 0.007%

    No Known Activations