© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135282
    Prev
    Next
    INDEX
    Explanations

    corrosion and its mitigation

    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_37_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
     rust
    0.96
    Rust
    0.83
     Rust
    0.81
    rust
    0.79
     rusting
    0.73
    锈
    0.73
     rusted
    0.71
     corrosion
    0.65
     rusty
    0.65
    錆
    0.60
    POSITIVE LOGITS
    textures
    0.39
    umetric
    0.37
     marcher
    0.36
    共和
    0.35
     textures
    0.35
    cay
    0.35
     textured
    0.34
     escol
    0.34
     mixing
    0.34
    ผู้ชมในสนาม
    0.34
    Activations Density 0.002%

    No Known Activations