© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166648
    Prev
    Next
    INDEX
    Explanations

    O-O

    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_56_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
    子
    1.37
     子
    1.02
    子が
    0.95
    子は
    0.89
    子的
    0.86
    子の
    0.86
     Child
    0.82
    Child
    0.80
    子上
    0.80
     tử
    0.79
    POSITIVE LOGITS
    ราย
    0.65
     ราย
    0.50
    ㄽ
    0.35
    сите
    0.34
    ரி
    0.34
    hender
    0.34
    覤
    0.34
     कामना
    0.33
    ral
    0.33
    رهای
    0.33
    Activations Density 0.001%

    No Known Activations