© 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. 156288
    Prev
    Next
    INDEX
    Explanations

    Australia

    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
    Dried
    0.38
     Knox
    0.37
    ዶች
    0.36
     Dried
    0.36
    ؤ
    0.35
     Thương
    0.35
    urgeon
    0.35
    prote
    0.34
     Isabella
    0.34
     Plates
    0.34
    POSITIVE LOGITS
    Kathy
    0.39
    }}^{-
    0.38
    ATM
    0.38
     Instantiate
    0.38
     brasil
    0.37
     Bootstrap
    0.37
    ިން
    0.37
    АТО
    0.36
    힙
    0.36
    𝐻
    0.36
    Activations Density 0.000%

    No Known Activations