© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217178
    Prev
    Next
    INDEX
    Explanations

    mis

    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_50_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
     Polic
    0.40
    aching
    0.39
    샌
    0.38
     бри
    0.38
    Polic
    0.38
    reece
    0.37
    чена
    0.37
    dinga
    0.37
    рија
    0.37
    ogens
    0.36
    POSITIVE LOGITS
    LT
    0.42
    lez
    0.40
     Zaragoza
    0.38
     soi
    0.37
    臊
    0.37
    Lag
    0.36
    띠
    0.36
    ИТ
    0.36
     naira
    0.35
     enak
    0.35
    Activations Density 0.002%

    No Known Activations