© 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. 206419
    Prev
    Next
    INDEX
    Explanations

    working relationship

    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_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
    an
    1.09
    <0x0D>
    0.87
     on
    0.86
    </h4>
    0.82
    }",
    0.80
    </h3>
    0.79
     externe
    0.78
     fenders
    0.77
     inclinations
    0.77
     (
    0.77
    POSITIVE LOGITS
    ”
    1.09
    ER
    1.00
    vention
    0.95
    ]
    0.94
    ﻴ
    0.94
     '
    0.93
    سازی
    0.93
    ד
    0.91
    .'
    0.90
    ellä
    0.89
    Activations Density 0.002%

    No Known Activations