© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228110
    Prev
    Next
    INDEX
    Explanations

    microclimate

    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_6_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
    x
    0.76
    arrival
    0.69
    dai
    0.69
    ).”
    0.68
    的
    0.67
    hetical
    0.65
    '=>
    0.65
    fields
    0.64
    ：
    0.62
     in
    0.61
    POSITIVE LOGITS
     on
    1.09
    נ
    1.06
    ید
    1.05
    м
    1.01
    オン
    1.00
    م
    0.98
    یت
    0.96
    ל
    0.92
    מ
    0.92
     or
    0.90
    Activations Density 0.000%

    No Known Activations