© 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. 228174
    Prev
    Next
    INDEX
    Explanations

    decongestants or decompiled

    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
    at
    0.93
    М
    0.83
    Б
    0.80
    м
    0.75
    down
    0.75
    Фор
    0.74
    К
    0.73
    дня
    0.73
    description
    0.72
    {{
    0.70
    POSITIVE LOGITS
     n
    0.92
    aj
    0.86
    وا
    0.86
    ли
    0.83
     has
    0.82
     permeability
    0.78
     and
    0.77
     foresee
    0.77
     outerwear
    0.77
     you
    0.77
    Activations Density 0.000%

    No Known Activations