© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21007
    Prev
    Next
    INDEX
    Explanations

    verb endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    巨大的
    0.41
    ested
    0.35
    规格
    0.35
     Nog
    0.34
     Goldman
    0.34
    美好的
    0.34
     fascinated
    0.33
    峻
    0.33
     अली
    0.32
    lastIndexOf
    0.32
    POSITIVE LOGITS
    izing
    1.41
    ening
    1.36
    ifying
    1.34
    IZING
    1.21
    ising
    1.18
    ishing
    1.15
    ating
    1.09
    uring
    1.06
    iting
    1.05
    ENING
    1.03
    Activations Density 0.083%

    No Known Activations