© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213846
    Prev
    Next
    INDEX
    Explanations

    multi

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     hydrophobic
    0.45
    umas
    0.39
    isot
    0.38
     morphogenesis
    0.37
    Gate
    0.37
    output
    0.37
    ouss
    0.36
    门
    0.36
     hydroph
    0.36
     pores
    0.36
    POSITIVE LOGITS
     mult
    0.90
     multi
    0.74
     Mult
    0.74
     Много
    0.73
    Mult
    0.72
     много
    0.71
     Multi
    0.70
     多
    0.68
    多
    0.66
     मल्टी
    0.66
    Activations Density 0.001%

    No Known Activations