© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88742
    Prev
    Next
    INDEX
    Explanations

    Standard Template Library

    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_3_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
    на
    0.88
    }=\
    0.72
    }$,
    0.69
    혔
    0.65
    ]$;
    0.64
    '});
    0.62
    യും
    0.62
    奭
    0.60
    ನನ್ನು
    0.59
    UM
    0.58
    POSITIVE LOGITS
    ar
    0.86
    er
    0.75
    u
    0.75
    ו
    0.75
    l
    0.75
    ul
    0.67
     {/*
    0.66
     кино
    0.63
    ligne
    0.63
     iure
    0.63
    Activations Density 0.002%

    No Known Activations