© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65437
    Prev
    Next
    INDEX
    Explanations

    CO and greenhouse gases

    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_41_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
     allongé
    0.40
     menuMobile
    0.38
     ベージュ
    0.37
     ब्लू
    0.36
    Рус
    0.36
     हायर
    0.36
    陨
    0.36
    ベージュ
    0.36
    slim
    0.35
    شاعر
    0.35
    POSITIVE LOGITS
     CO
    0.73
    CO
    0.57
     tiers
    0.44
    二氧化
    0.44
     carbonic
    0.42
     bi
    0.41
    xty
    0.41
     emerging
    0.40
    瘤
    0.40
     carbon
    0.39
    Activations Density 0.023%

    No Known Activations