© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175269
    Prev
    Next
    INDEX
    Explanations

    top/upper body

    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_20_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
     AMO
    0.48
     redefined
    0.48
    huis
    0.46
     NMC
    0.42
     paleo
    0.42
     －
    0.42
     норма
    0.41
    が進
    0.41
    र्मा
    0.40
    -\{
    0.40
    POSITIVE LOGITS
    åd
    0.43
    example
    0.42
    দিগের
    0.42
    judul
    0.41
    anh
    0.40
    owned
    0.40
     আগে
    0.40
    时间和
    0.40
    ẵn
    0.39
    connection
    0.39
    Activations Density 0.000%

    No Known Activations