© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16741
    Prev
    Next
    INDEX
    Explanations

    constructor ( )

    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_34_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
    쪼
    0.38
     Consecutive
    0.37
     cosecha
    0.37
    toolStripButton
    0.37
     supporter
    0.37
     pollutant
    0.36
     goodies
    0.35
     पदार्थ
    0.35
    弥
    0.35
    split
    0.34
    POSITIVE LOGITS
     equipped
    0.42
    த்திற்காக
    0.41
    зик
    0.41
    无论
    0.40
     preparing
    0.40
    Bounded
    0.39
     anywhere
    0.38
     menyiapkan
    0.38
     príp
    0.36
    無論
    0.36
    Activations Density 0.001%

    No Known Activations