© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123262
    Prev
    Next
    INDEX
    Explanations

    government bonds, gun violence, emissions, grid, mourning, archives

    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_3_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
    𝐥
    0.77
    𝐯
    0.75
    на
    0.74
    聁
    0.73
    𝐚
    0.72
    𝐭
    0.71
    𝐲
    0.67
    ree
    0.67
    𝐩
    0.66
    𝐢
    0.65
    POSITIVE LOGITS
    ir
    0.77
    ید
    0.71
    Tipo
    0.67
     کھیلو
    0.67
     ejecutar
    0.66
     epicenter
    0.65
     alimentare
    0.65
    해서
    0.64
     groaned
    0.64
    ۔
    0.64
    Activations Density 0.001%

    No Known Activations