© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3412
    Prev
    Next
    INDEX
    Explanations

    adverbs describing manner (heavily, carefully)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    воре
    0.60
    슨
    0.56
    uch
    0.56
     Versch
    0.54
     Jeder
    0.51
    Vc
    0.51
     كون
    0.50
     pieno
    0.50
     Collaborate
    0.49
     आफ्
    0.49
    POSITIVE LOGITS
    ف
    0.69
    人
    0.53
    gs
    0.52
    p
    0.50
    しかし
    0.49
     equilibria
    0.49
     gentamicin
    0.49
    Bài
    0.48
    에
    0.48
    ב
    0.47
    Activations Density 0.131%

    No Known Activations