© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131396
    Prev
    Next
    INDEX
    Explanations

    defective

    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_1_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
    ק
    1.02
    د
    0.98
    ла
    0.93
     énon
    0.92
     tokamaks
    0.90
    omers
    0.90
    uity
    0.88
     accuracies
    0.88
     inclinations
    0.87
    लु
    0.86
    POSITIVE LOGITS
    (
    1.66
    }
    1.28
    কে
    1.27
    s
    1.21
    -
    1.13
    ের
    1.00
    \
    0.99
    يل
    0.98
    ми
    0.97
    </u>
    0.96
    Activations Density 0.000%

    No Known Activations