© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180003
    Prev
    Next
    INDEX
    Explanations

    comparison and contrast

    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_29_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
     iliş
    0.37
     út
    0.36
    ሓ
    0.35
     roof
    0.34
     subscription
    0.34
     ponte
    0.34
     Rossa
    0.34
    觕
    0.34
    ื้อง
    0.33
     denoted
    0.33
    POSITIVE LOGITS
     compared
    0.51
    compared
    0.47
    Compared
    0.44
     dibandingkan
    0.42
     Compared
    0.41
    比べて
    0.41
     Compare
    0.40
     dibanding
    0.40
    对比
    0.40
    indah
    0.39
    Activations Density 0.009%

    No Known Activations