© 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. 204322
    Prev
    Next
    INDEX
    Explanations

    ora

    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
    ଉ
    0.38
    ποιη
    0.38
    ļu
    0.35
    υχ
    0.35
    larım
    0.35
    ्युन
    0.34
     blistering
    0.34
    OCATION
    0.34
    USTOM
    0.34
    orch
    0.34
    POSITIVE LOGITS
    伈
    0.38
     Я
    0.38
    YOU
    0.38
    컹
    0.37
    aked
    0.37
    赸
    0.37
    मो
    0.36
     程序
    0.36
    Я
    0.36
    方程
    0.35
    Activations Density 0.001%

    No Known Activations