© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235003
    Prev
    Next
    INDEX
    Explanations

    do

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     çö
    0.45
     رضی
    0.43
    omerase
    0.41
     bors
    0.37
    𝘼
    0.37
     гипсо
    0.36
     ذره
    0.35
     sortir
    0.35
    ന്നെ
    0.34
    ሬ
    0.34
    POSITIVE LOGITS
    anyard
    0.40
    processes
    0.39
     सिक
    0.38
     Intelligent
    0.38
    },-
    0.38
     Dest
    0.37
    idable
    0.37
    perl
    0.37
    spra
    0.37
    amand
    0.37
    Activations Density 0.002%

    No Known Activations