© 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. 36923
    Prev
    Next
    INDEX
    Explanations

    Arco, Ashwagandha, CO, wad

    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
     was
    0.92
    }
    0.80
    PL
    0.71
     reuni
    0.69
     garanti
    0.68
    CAN
    0.67
    CZ
    0.67
    BJP
    0.66
    数据
    0.66
    '}
    0.65
    POSITIVE LOGITS
    να
    0.77
    них
    0.73
    այն
    0.68
    erasan
    0.66
    aying
    0.66
    -
    0.66
    il
    0.63
    ்த்து
    0.60
    ль
    0.59
    را
    0.58
    Activations Density 0.004%

    No Known Activations