© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90884
    Prev
    Next
    INDEX
    Explanations

    arr

    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_60_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
     ].
    0.48
     ]:
    0.45
     ];
    0.43
    radiation
    0.42
     }-\
    0.41
    single
    0.41
     ][
    0.39
     ]);
    0.39
     ]];
    0.39
     »,
    0.38
    POSITIVE LOGITS
    )
    0.90
    }
    0.76
    ')
    0.65
    ?)
    0.65
    ")
    0.62
    __)
    0.57
    ]
    0.55
    »)
    0.54
    '')
    0.54
    ),
    0.53
    Activations Density 0.000%

    No Known Activations