© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44318
    Prev
    Next
    INDEX
    Explanations

    to do this

    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_22_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
     —
    0.29
     they
    0.28
     قالب
    0.28
     вони
    0.28
     rags
    0.27
    懇
    0.27
    说什么
    0.27
     họ
    0.27
    左
    0.27
     mounts
    0.27
    POSITIVE LOGITS
    edinte
    0.31
    らえる
    0.29
    isierte
    0.29
    Voir
    0.28
    bruck
    0.28
    AllFilesIn
    0.27
    следования
    0.27
     vedere
    0.27
    বাহিত
    0.26
    ূর্ণ
    0.26
    Activations Density 0.004%

    No Known Activations