© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 206380
    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_46_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
     confound
    0.38
    ங்குக
    0.37
    ৪৩
    0.35
    cea
    0.35
     ಘೋಷ
    0.34
    ২
    0.34
    getSystemService
    0.34
     साइनस
    0.34
    ศ
    0.34
     iii
    0.34
    POSITIVE LOGITS
     your
    0.49
     vaše
    0.48
    您的
    0.47
     vaš
    0.45
     Your
    0.45
    your
    0.45
    Your
    0.43
    YOUR
    0.43
     вашу
    0.43
     Ihren
    0.42
    Activations Density 0.000%

    No Known Activations