© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 4090
    Prev
    Next
    INDEX
    Explanations

    blue

    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_44_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
     MMM
    0.44
     ld
    0.40
    াজনক
    0.38
    到时候
    0.38
    ESSMENT
    0.38
    ']."
    0.37
     dd
    0.37
    াকিং
    0.37
    }.",
    0.37
     કાર
    0.36
    POSITIVE LOGITS
     Blue
    0.63
    Blue
    0.60
     blue
    0.58
    blue
    0.57
    BLUE
    0.56
     BLUE
    0.50
    蓝
    0.49
     Host
    0.48
    ブルー
    0.46
    藍
    0.46
    Activations Density 0.012%

    No Known Activations