© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161769
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ătoare
    1.11
     Ε
    0.98
    ali
    0.97
    anch
    0.91
     Parece
    0.91
    р
    0.89
    ㅁ
    0.87
    abouts
    0.86
     radiate
    0.86
    edes
    0.85
    POSITIVE LOGITS
    3
    1.34
    ל
    1.26
    一
    1.25
    ح
    1.21
    ون
    1.09
    ت
    1.07
    ু
    1.03
    um
    1.02
    но
    0.98
    ru
    0.92
    Activations Density 0.000%

    No Known Activations