© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151420
    Prev
    Next
    INDEX
    Explanations

    iPhone 14 Pro Max cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     involved
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.34
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.32
     differs
    0.32
    involved
    0.31
    sev
    0.30
    酬
    0.30
    ↵↵↵↵↵↵↵
    0.30
    lable
    0.30
    POSITIVE LOGITS
    Dopo
    0.37
    Depois
    0.33
    væ
    0.32
     cerveau
    0.32
     після
    0.32
     Merkezi
    0.32
     sağlıklı
    0.32
    частли
    0.31
     后
    0.31
    ếp
    0.30
    Activations Density 0.005%

    No Known Activations