© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88118
    Prev
    Next
    INDEX
    Explanations

    control flow

    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_3_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
     controladores
    0.71
     controla
    0.66
    、
    0.65
     disturb
    0.64
    и
    0.64
    Controller
    0.61
     controlador
    0.61
     concede
    0.60
     do
    0.60
     इसकी
    0.60
    POSITIVE LOGITS
    ytt
    0.71
    set
    0.69
    oj
    0.64
    aft
    0.63
    م
    0.63
    นาย
    0.62
    ා
    0.61
     étage
    0.61
    am
    0.60
    bdb
    0.59
    Activations Density 0.009%

    No Known Activations