© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85982
    Prev
    Next
    INDEX
    Explanations

    The Guardian and Telegraph

    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_18_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
    诨
    0.39
    𝖑
    0.38
    åk
    0.36
    ហា
    0.36
    ल
    0.35
    لوں
    0.35
     hopping
    0.34
     Varan
    0.34
    कियां
    0.34
     Marne
    0.34
    POSITIVE LOGITS
    規模
    0.36
    מי
    0.35
    ાઇ
    0.34
     სას
    0.33
    ギア
    0.33
    放送
    0.32
    肥
    0.32
    日子
    0.32
     ليا
    0.32
     ديال
    0.32
    Activations Density 0.000%

    No Known Activations