© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32749
    Prev
    Next
    INDEX
    Explanations

    processing language for creatives

    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
    ropo
    0.42
    魘
    0.41
    ACY
    0.41
     skil
    0.40
    配置
    0.40
    Employee
    0.38
    employer
    0.38
     mf
    0.36
    ОР
    0.36
     ይቀ
    0.36
    POSITIVE LOGITS
     upstairs
    0.39
    ␣
    0.39
     ProRes
    0.38
    allelujah
    0.38
     Spiel
    0.38
    asmine
    0.37
    вис
    0.37
    inect
    0.36
     biota
    0.36
     probing
    0.35
    Activations Density 0.012%

    No Known Activations