© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233309
    Prev
    Next
    INDEX
    Explanations

    liquid

    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_32_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
    ليات
    0.42
     handic
    0.41
    ज़
    0.37
     rue
    0.37
    feu
    0.37
    heiros
    0.36
     休
    0.36
     фут
    0.36
     griff
    0.35
     UE
    0.35
    POSITIVE LOGITS
     Liquid
    0.91
    Liquid
    0.88
     liquid
    0.81
    liquid
    0.80
    液
    0.79
    Liqu
    0.70
     liqu
    0.70
     Liqu
    0.69
     液
    0.68
    液体
    0.66
    Activations Density 0.004%

    No Known Activations