© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24170
    Prev
    Next
    INDEX
    Explanations

    say "r" 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_56_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
     rights
    1.05
     права
    0.99
     direito
    0.98
    權
    0.98
    权
    0.97
     Rights
    0.96
    rights
    0.94
    Rights
    0.94
    권
    0.94
    権
    0.93
    POSITIVE LOGITS
     Regener
    0.44
    Ris
    0.39
    inalg
    0.38
     ग़
    0.38
    })$
    0.38
     españ
    0.37
     dành
    0.37
     Dafür
    0.37
     शिक्ष
    0.37
    concat
    0.37
    Activations Density 0.006%

    No Known Activations