© 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. 204516
    Prev
    Next
    INDEX
    Explanations

    prioritize obtaining

    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
    Stephanie
    0.45
    nolds
    0.41
     poorly
    0.40
    ='+
    0.39
    Steph
    0.39
    irina
    0.39
     stereotyp
    0.38
     ova
    0.38
    Reprodu
    0.38
     spits
    0.37
    POSITIVE LOGITS
    的所有
    0.42
    所有
    0.40
    multiple
    0.39
     ভালো
    0.39
    सभी
    0.38
     Multiple
    0.38
     どれ
    0.38
    繖
    0.38
    json
    0.37
     متح
    0.37
    Activations Density 0.002%

    No Known Activations