© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51163
    Prev
    Next
    INDEX
    Explanations

    psychedelics and recreational drugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ー
    0.52
    즈
    0.50
    海の
    0.50
    ز
    0.50
    ėl
    0.48
    कोण
    0.48
    зда
    0.48
    μπο
    0.46
    ः
    0.46
    ელის
    0.46
    POSITIVE LOGITS
     alkaloids
    0.54
    }
    0.50
     }
    0.50
     $
    0.48
     semblable
    0.48
     ﺍ
    0.47
    ।
    0.46
     lassen
    0.46
     blankets
    0.45
    ]
    0.45
    Activations Density 0.062%

    No Known Activations