© 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. 178314
    Prev
    Next
    INDEX
    Explanations

    rom

    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
     Washington
    0.44
    Washington
    0.43
    URU
    0.40
    硕
    0.40
    చి
    0.39
    lena
    0.38
     Soh
    0.38
    WAM
    0.37
     washing
    0.37
    ASHINGTON
    0.37
    POSITIVE LOGITS
    neat
    0.43
    iej
    0.42
    ീയ
    0.41
     iee
    0.41
    iep
    0.39
    楮
    0.38
    ೀಯ
    0.38
     roommates
    0.37
     степен
    0.37
    ائن
    0.36
    Activations Density 0.000%

    No Known Activations