© 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. 17534
    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_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
    ecimento
    0.49
    мыс
    0.48
     нарушение
    0.48
    }|^{
    0.45
    ‡
    0.45
    }:
    0.45
     страда
    0.44
    tà
    0.44
    oop
    0.44
     tartoz
    0.44
    POSITIVE LOGITS
    <0xE3>
    0.52
    ポイント
    0.51
     aplik
    0.49
    Luxury
    0.49
     luxuries
    0.47
     dokter
    0.47
     loro
    0.46
     vecchio
    0.46
     lux
    0.46
     Mỗi
    0.46
    Activations Density 0.000%

    No Known Activations