© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198182
    Prev
    Next
    INDEX
    Explanations

    R tokens

    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_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
     channel
    0.40
    channel
    0.38
     Ethan
    0.38
    кот
    0.38
     眼
    0.38
     core
    0.37
    Channel
    0.36
    Toxic
    0.36
     wing
    0.36
     Toxicity
    0.36
    POSITIVE LOGITS
     R
    0.68
     الر
    0.56
    Ｒ
    0.47
    R
    0.47
    RZ
    0.39
    INTER
    0.39
     Morris
    0.39
    diamond
    0.39
    )|\
    0.38
    蝴蝶
    0.38
    Activations Density 0.027%

    No Known Activations