© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195255
    Prev
    Next
    INDEX
    Explanations

    sayings and arguments

    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_50_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
     Rak
    0.43
    >∈</
    0.42
     rak
    0.39
    quinas
    0.39
    σεων
    0.38
     Nxc
    0.38
    żenie
    0.37
    ologien
    0.37
    োলজি
    0.37
    鉾
    0.37
    POSITIVE LOGITS
    vise
    0.45
    VSLU
    0.40
    vans
    0.39
    ТО
    0.39
     visceral
    0.39
     adsor
    0.38
    videos
    0.37
     Бы
    0.37
    emps
    0.37
     vans
    0.36
    Activations Density 0.000%

    No Known Activations