© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 204631
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     hubs
    0.38
     fallout
    0.35
    Pixel
    0.34
     جنہوں
    0.34
     وحد
    0.33
    Rogers
    0.33
    ૂર્
    0.33
    [:
    0.33
     원하는
    0.33
     pixels
    0.32
    POSITIVE LOGITS
     deus
    0.48
     stealing
    0.46
    люб
    0.42
     steal
    0.41
    pios
    0.41
    꽉
    0.40
     Association
    0.39
     Genocide
    0.38
    ensia
    0.38
    plate
    0.38
    Activations Density 0.000%

    No Known Activations