© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151446
    Prev
    Next
    INDEX
    Explanations

    countries like the United, UK

    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_23_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
     Certainly
    0.45
     Baroque
    0.45
     Subaru
    0.45
     Peach
    0.44
     Mask
    0.44
    ંત્રી
    0.44
    ጐ
    0.43
     dragonfly
    0.43
     Hokkaido
    0.43
     Til
    0.42
    POSITIVE LOGITS
    requested
    0.44
    consum
    0.41
    adu
    0.41
    ớm
    0.39
    尿
    0.39
    ષ્
    0.39
    说明
    0.39
    ancis
    0.39
    を一
    0.38
    dated
    0.38
    Activations Density 0.002%

    No Known Activations