© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200659
    Prev
    Next
    INDEX
    Explanations

    Them

    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_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
     Frederick
    0.41
     beans
    0.40
    Frederick
    0.39
    har
    0.38
     Cul
    0.38
     Darlington
    0.38
     bean
    0.38
    න
    0.36
     জাহাঙ্গীর
    0.36
    Goss
    0.36
    POSITIVE LOGITS
    burgh
    0.51
     deles
    0.47
     őket
    0.46
    พวก
    0.45
    它们
    0.42
     delas
    0.42
    他们
    0.42
     Them
    0.41
     них
    0.41
     them
    0.41
    Activations Density 0.007%

    No Known Activations