© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194072
    Prev
    Next
    INDEX
    Explanations

    displayed data structures and programming constructs

    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_15_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
    ta
    0.58
    th
    0.58
    而是
    0.57
    mx
    0.53
    taa
    0.52
    cs
    0.51
    stå
    0.51
    i
    0.51
    foro
    0.50
    whel
    0.50
    POSITIVE LOGITS
     gegevens
    0.59
     símbolo
    0.55
     títulos
    0.53
     primeros
    0.52
     symbole
    0.51
     números
    0.50
     остров
    0.50
     aujourd
    0.50
    וד
    0.48
     titles
    0.48
    Activations Density 0.001%

    No Known Activations