© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30020
    Prev
    Next
    INDEX
    Explanations

    code snippets and language keywords

    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_40_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
     কেউই
    0.42
    Monitor
    0.41
     Mickey
    0.40
    prepared
    0.39
    객
    0.39
     spectroscopic
    0.39
    Hiking
    0.39
    Lavender
    0.39
    Stop
    0.38
    STOP
    0.38
    POSITIVE LOGITS
     tenets
    0.40
    獐
    0.38
     bó
    0.36
     assertEquals
    0.36
     ausgezeichnet
    0.36
     স্ব
    0.35
     inset
    0.35
    Manus
    0.35
     estrategias
    0.35
     álgebra
    0.35
    Activations Density 0.002%

    No Known Activations