© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104816
    Prev
    Next
    INDEX
    Explanations

    metric space properties

    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_44_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
    γκ
    0.48
    VS
    0.40
    ᠯ
    0.39
    Γ
    0.38
    Kansas
    0.38
    zk
    0.37
     бро
    0.37
    Total
    0.37
     Drawing
    0.36
    ẩu
    0.36
    POSITIVE LOGITS
     decirle
    0.45
    优点
    0.41
     শর্ত
    0.40
    聸
    0.40
    )`;
    0.39
    謗
    0.39
    ന്ഥ
    0.38
     именно
    0.37
     exf
    0.37
     عالية
    0.37
    Activations Density 0.001%

    No Known Activations