© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68935
    Prev
    Next
    INDEX
    Explanations

    say "u" words

    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_51_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
    acyl
    0.40
     aur
    0.38
    慈
    0.37
    ova
    0.36
     moral
    0.36
     ભે
    0.36
    creativecommons
    0.35
     Taur
    0.35
    ]+"
    0.35
    בים
    0.35
    POSITIVE LOGITS
    ule
    0.75
    ules
    0.70
    ULES
    0.69
    ULE
    0.68
     ul
    0.63
    ula
    0.61
    ular
    0.59
    ulate
    0.57
     Ul
    0.57
     ult
    0.55
    Activations Density 0.001%

    No Known Activations