© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10260
    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_40_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
    罅
    0.36
    ophores
    0.35
    運転
    0.34
     духо
    0.34
     inscrit
    0.34
     Zac
    0.34
    鹌
    0.34
     traduire
    0.33
     メル
    0.33
    酢
    0.33
    POSITIVE LOGITS
    sman
    0.41
    íbrio
    0.38
    her
    0.37
     gating
    0.36
    że
    0.36
     Gat
    0.36
    윅
    0.36
    lazy
    0.35
    साब
    0.35
     thấm
    0.35
    Activations Density 0.031%

    No Known Activations