© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246101
    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_40_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
    plotting
    0.43
     黑
    0.43
    ेक्ट
    0.40
    shap
    0.40
    webservices
    0.40
    teen
    0.38
     batalha
    0.36
    ⠛
    0.36
    jango
    0.36
    ṗ
    0.36
    POSITIVE LOGITS
     initials
    0.42
     Transplantation
    0.39
     drenched
    0.36
    computers
    0.35
    ανο
    0.35
    ដើ
    0.35
    Compl
    0.35
    ovington
    0.35
    ensitivity
    0.35
    या
    0.34
    Activations Density 0.000%

    No Known Activations