© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231243
    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_6_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
    ang
    1.18
    ak
    0.98
    ave
    0.95
    :
    0.94
    ot
    0.91
     Mammoth
    0.91
    aan
    0.91
    ).
    0.90
     Calvary
    0.90
     PROBLEM
    0.88
    POSITIVE LOGITS
    ת
    1.16
    تر
    1.10
    리
    1.09
    ב
    1.08
    تق
    1.05
    ف
    1.01
    اد
    1.00
    ה
    0.98
    ма
    0.98
    ำ
    0.98
    Activations Density 0.000%

    No Known Activations