© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116071
    Prev
    Next
    INDEX
    Explanations

    also introduces further details

    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_27_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
     infinitely
    0.40
     almost
    0.40
     seamlessly
    0.37
     Monster
    0.36
     award
    0.36
     quickly
    0.35
    Entity
    0.35
     “
    0.35
     Trust
    0.35
     resized
    0.35
    POSITIVE LOGITS
    ubjects
    0.41
     dukkham
    0.40
     предметов
    0.40
     predmet
    0.40
    用い
    0.39
     prog
    0.39
     bondage
    0.38
     предмет
    0.38
     artigos
    0.38
     ligação
    0.37
    Activations Density 0.020%

    No Known Activations