© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198476
    Prev
    Next
    INDEX
    Explanations

    LLaMA model

    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
    Net
    0.45
     Net
    0.41
    קה
    0.40
    Kath
    0.40
    קב
    0.40
     Peki
    0.39
    ਾਕ
    0.39
    絠
    0.38
    काश
    0.38
     Kā
    0.38
    POSITIVE LOGITS
     lo
    0.48
    йда
    0.46
     lobe
    0.43
    ディオ
    0.42
     nodeId
    0.41
     lob
    0.40
     ida
    0.40
     Lo
    0.39
    镓
    0.39
    bulb
    0.39
    Activations Density 0.010%

    No Known Activations