© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31547
    Prev
    Next
    INDEX
    Explanations

    for good reason

    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_7_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
     be
    1.12
    0.89
    (
    0.76
    I
    0.75
     l
    0.72
    för
    0.70
    是
    0.69
    inations
    0.66
     :
    0.65
     i
    0.65
    POSITIVE LOGITS
    an
    1.13
    𝓭
    1.00
    𝚇
    0.94
    ഡ്
    0.94
    靝
    0.93
    on
    0.92
     同じ
    0.92
    𝑳
    0.92
     ロー
    0.91
    ⓤ
    0.89
    Activations Density 0.003%

    No Known Activations