© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34286
    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_50_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
    ্লো
    0.40
    Л
    0.40
     Palms
    0.40
     ux
    0.37
    startX
    0.36
     sheared
    0.36
    locationX
    0.36
    𝐗
    0.36
    Fancy
    0.35
    濤
    0.35
    POSITIVE LOGITS
     summit
    0.42
     Missy
    0.40
    inari
    0.39
     ert
    0.38
    茵
    0.38
     Erie
    0.38
     spre
    0.38
    Jackie
    0.38
     Reef
    0.37
    Summit
    0.37
    Activations Density 0.000%

    No Known Activations