© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31466
    Prev
    Next
    INDEX
    Explanations

    depth, temperature, stainless

    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_40_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
    壁
    0.43
     hag
    0.39
     waterline
    0.39
     wall
    0.38
     BAT
    0.37
    坩
    0.37
     lục
    0.37
    ዉ
    0.36
     শীতল
    0.36
    ిత
    0.36
    POSITIVE LOGITS
    горит
    0.42
     Miloš
    0.41
     যুগ
    0.38
     đức
    0.38
     danced
    0.38
     fringilla
    0.38
     लें
    0.37
    क्रोस
    0.37
    ≅
    0.37
    Sliced
    0.37
    Activations Density 0.040%

    No Known Activations