© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206736
    Prev
    Next
    INDEX
    Explanations

    understand or define learning objectives

    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_25_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
     ബു
    0.43
    鲔
    0.40
     Prisma
    0.38
     PBS
    0.38
    fund
    0.37
     बु
    0.37
    funding
    0.36
    jumlah
    0.36
    🤤
    0.36
    ධ
    0.35
    POSITIVE LOGITS
     conversely
    0.41
     alternatively
    0.35
     landslide
    0.35
     frantic
    0.34
     delante
    0.34
     Conversely
    0.33
     momencie
    0.33
     بلکه
    0.32
     counted
    0.32
     phospholip
    0.32
    Activations Density 0.001%

    No Known Activations