© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108048
    Prev
    Next
    INDEX
    Explanations

    Victorian Era

    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_1_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
    ى
    1.23
    ן
    1.15
    يث
    1.10
    지
    1.06
    ↵
    1.05
    ৯
    1.02
    好
    0.99
    واد
    0.97
    b
    0.97
    টি
    0.95
    POSITIVE LOGITS
    uk
    1.16
    tu
    1.08
     леса
    1.01
     основ
    0.99
    :
    0.95
    tra
    0.91
    റൽ
    0.91
     are
    0.91
     doctora
    0.90
     модель
    0.89
    Activations Density 0.001%

    No Known Activations