© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17387
    Prev
    Next
    INDEX
    Explanations

    frozen conflict or dormant pathways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
     bowled
    0.50
     swayed
    0.50
    德
    0.50
    ýv
    0.48
    酸
    0.47
     fouled
    0.47
    题目
    0.47
     bảy
    0.47
     varía
    0.47
    ズ
    0.46
    POSITIVE LOGITS
     อื่น
    0.57
    ፣
    0.56
    }]$.
    0.53
    outputText
    0.53
     ബന്ധ
    0.51
     granulation
    0.49
     உடன்
    0.49
    ्ञ
    0.49
    }}.
    0.49
     pemerintahan
    0.49
    Activations Density 0.025%

    No Known Activations