© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195458
    Prev
    Next
    INDEX
    Explanations

    Bomba

    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_4_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
    म
    1.27
    м
    1.08
    م
    1.08
    ي
    1.06
    り
    0.98
    و
    0.98
    ول
    0.95
    ور
    0.95
    ম
    0.94
    자
    0.94
    POSITIVE LOGITS
    ia
    1.06
    ]
    1.02
    í
    1.01
     have
    0.98
    ü
    0.97
    ”
    0.97
    ash
    0.95
     atteinte
    0.94
    ing
    0.91
    }
    0.90
    Activations Density 0.002%

    No Known Activations