© 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. 249900
    Prev
    Next
    INDEX
    Explanations

    assignment and operation

    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
    ється
    0.45
    ۔۔
    0.44
     Lol
    0.40
     commun
    0.39
     UIF
    0.39
     RING
    0.39
    \/}
    0.38
     qs
    0.38
     Reward
    0.37
     Worlds
    0.36
    POSITIVE LOGITS
    sub
    0.39
    asks
    0.36
    ingredient
    0.36
    uch
    0.35
    ****",
    0.35
    ключение
    0.34
    announce
    0.34
    awt
    0.33
     কাজল
    0.33
    azan
    0.33
    Activations Density 0.009%

    No Known Activations