© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230724
    Prev
    Next
    INDEX
    Explanations

    school

    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_6_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
     လုပ်
    0.98
    ]
    0.96
    )
    0.93
    unches
    0.86
    }
    0.85
    rin
    0.83
    icians
    0.82
     Tvam
    0.80
     Difficult
    0.80
     များ
    0.79
    POSITIVE LOGITS
    ת
    1.11
    ت
    1.03
    ة
    1.02
    ك
    1.01
    ول
    1.00
    2
    0.94
    ле
    0.93
    خ
    0.88
    ה
    0.86
    ో
    0.86
    Activations Density 0.001%

    No Known Activations