© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251308
    Prev
    Next
    INDEX
    Explanations

    nature and scenery

    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
     قبر
    0.42
     двер
    0.39
    optical
    0.39
    Gab
    0.39
     retrieve
    0.37
    광
    0.37
    oghi
    0.37
    离
    0.36
    <unused494>
    0.36
    離
    0.35
    POSITIVE LOGITS
    原
    0.42
    芏
    0.42
    繆
    0.38
     मू
    0.38
    ム
    0.37
    坫
    0.37
     Ton
    0.36
     Tween
    0.36
     Ground
    0.36
    adka
    0.36
    Activations Density 0.000%

    No Known Activations