© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89037
    Prev
    Next
    INDEX
    Explanations

    logistics, companies, anterior, circle, iq

    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_3_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
    ت
    0.86
    ي
    0.69
    可以
    0.69
    י
    0.64
     Brake
    0.63
     Слова
    0.63
     foothold
    0.61
    ท
    0.59
     brake
    0.59
    보다
    0.59
    POSITIVE LOGITS
    are
    0.81
    s
    0.80
    p
    0.77
    SA
    0.75
    ian
    0.74
    ls
    0.72
    re
    0.70
    SHO
    0.70
    lan
    0.66
     individuales
    0.64
    Activations Density 0.000%

    No Known Activations