© 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. 88058
    Prev
    Next
    INDEX
    Explanations

    model, lettuce, loss

    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
     are
    0.80
    ﻚ
    0.71
     dedu
    0.70
     уто
    0.69
     daje
    0.68
     ۴
    0.67
     conceptually
    0.66
    ுகிற
    0.66
     palma
    0.66
     confronting
    0.66
    POSITIVE LOGITS
    ב
    0.93
    sz
    0.82
    لي
    0.82
    స
    0.82
    ла
    0.81
    ler
    0.81
    dh
    0.81
    log
    0.80
    ле
    0.79
    la
    0.79
    Activations Density 0.003%

    No Known Activations