© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196734
    Prev
    Next
    INDEX
    Explanations

    confirming understanding

    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_27_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
     Unesco
    0.37
     terrain
    0.35
    奏
    0.35
    separator
    0.35
    rosis
    0.35
    结局
    0.34
    礁
    0.34
    ின
    0.34
    rede
    0.34
    owicz
    0.34
    POSITIVE LOGITS
     lä
    0.38
     হলে
    0.38
     sloth
    0.37
     meticulously
    0.37
     Gör
    0.37
     থাকলে
    0.37
     громадян
    0.36
     memahami
    0.35
     /
    0.35
     Else
    0.35
    Activations Density 0.012%

    No Known Activations