© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158081
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ので
    1.06
    ן
    1.03
    ﺄ
    1.02
    Ꭺ
    1.02
    是對
    1.00
    ם
    0.98
    ාවිත
    0.96
    ඪ
    0.96
    س
    0.95
    ഡ്
    0.93
    POSITIVE LOGITS
    n
    1.73
    ed
    1.69
    m
    1.59
    en
    1.58
    an
    1.57
    et
    1.57
    la
    1.48
    j
    1.45
    i
    1.42
    es
    1.37
    Activations Density 0.000%

    No Known Activations