© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110140
    Prev
    Next
    INDEX
    Explanations

    exploiting

    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_2_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
    themed
    1.04
    牘
    0.99
    дет
    0.98
     வெப்சீரி
    0.95
    зіно
    0.94
    rated
    0.91
    the
    0.90
    larının
    0.90
     인해
    0.90
    ured
    0.89
    POSITIVE LOGITS
    (
    1.98
    is
    1.41
    '
    1.39
    -
    1.34
                    
    1.32
    يت
    1.32
    i
    1.30
    ↵↵
    1.27
    ות
    1.27
    ী
    1.24
    Activations Density 0.000%

    No Known Activations