© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52397
    Prev
    Next
    INDEX
    Explanations

    take a moment to

    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_31_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
     قصير
    0.40
    娱
    0.35
    веде
    0.35
    AccessException
    0.35
     quince
    0.34
     Amts
    0.34
    chlorate
    0.34
     زود
    0.34
     Perk
    0.34
     Ambos
    0.33
    POSITIVE LOGITS
     livid
    0.48
     manager
    0.45
    管理器
    0.43
     মিনিটে
    0.42
    ⏫
    0.42
     ansiedad
    0.42
     Manager
    0.40
     cens
    0.39
     센
    0.39
    konto
    0.38
    Activations Density 0.001%

    No Known Activations