© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18209
    Prev
    Next
    INDEX
    Explanations

    digital currencies, decentralization

    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
     Iterable
    0.42
    어로
    0.39
     ''){
    0.37
    )\\
    0.36
    quée
    0.36
     kori
    0.36
    )}$-
    0.36
    漠
    0.35
     regal
    0.35
    <unused50>
    0.35
    POSITIVE LOGITS
     decentral
    1.26
     decentralized
    1.20
     Decentral
    1.10
     centralization
    0.70
     devolved
    0.68
     centralized
    0.66
     centralised
    0.65
     devol
    0.62
    entral
    0.54
    Dec
    0.54
    Activations Density 0.023%

    No Known Activations