© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167106
    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_34_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
     mitigation
    0.46
     mitig
    0.45
     mitigated
    0.43
     Mitigation
    0.42
     mitigating
    0.41
    釈
    0.38
    参照
    0.38
     mitigate
    0.38
     Pathfinder
    0.37
     নথি
    0.37
    POSITIVE LOGITS
    homes
    0.36
     ceo
    0.36
    odb
    0.36
     coma
    0.36
     someplace
    0.35
     انتظامی
    0.35
    碗
    0.35
    anto
    0.35
    home
    0.34
     invál
    0.34
    Activations Density 0.000%

    No Known Activations