© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198760
    Prev
    Next
    INDEX
    Explanations

    charged

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Assignments
    0.40
    ອງ
    0.36
    istiche
    0.36
     करते
    0.36
    矮
    0.36
     प्रत्या
    0.35
    奭
    0.35
    ダウン
    0.35
     quadrupole
    0.35
    )*((
    0.35
    POSITIVE LOGITS
     suma
    0.40
     fines
    0.39
     tiềm
    0.38
     Eugen
    0.37
     aux
    0.36
    along
    0.36
    bsch
    0.36
     Kirkland
    0.36
     fined
    0.36
    aux
    0.36
    Activations Density 0.001%

    No Known Activations