© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198309
    Prev
    Next
    INDEX
    Explanations

    steel shapes and structural components

    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_12_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
    皖
    0.63
    Há
    0.60
    há
    0.59
    对于
    0.58
     राजपूत
    0.58
     하
    0.55
     patterning
    0.55
    到了
    0.55
    동안
    0.55
    汚れ
    0.54
    POSITIVE LOGITS
    eringen
    0.55
    jah
    0.53
     director
    0.53
    ਜ਼
    0.51
    ado
    0.51
    anden
    0.51
    atir
    0.51
    +
    0.49
     "";
    0.49
    atik
    0.48
    Activations Density 0.002%

    No Known Activations