© 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. 171811
    Prev
    Next
    INDEX
    Explanations

    introductions to concepts

    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
     N
    0.48
     {
    0.47
     spongy
    0.46
     Λ
    0.44
     segregation
    0.44
    ：
    0.43
     j
    0.43
     Location
    0.43
     Н
    0.43
    uns
    0.43
    POSITIVE LOGITS
    رځ
    0.51
     analis
    0.45
     pembuatan
    0.42
     quotid
    0.42
     conhecida
    0.41
    こともある
    0.40
     pedibus
    0.40
     perspici
    0.40
     কলেজে
    0.39
    또한
    0.39
    Activations Density 0.000%

    No Known Activations