© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16033
    Prev
    Next
    INDEX
    Explanations

    words related to discussing or describing research articles or case studies and their data/results

    oai_token-act-pair · gemini-2.0-flash

    discussing, exploring, presenting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.74
     purpoſe
    -0.73
     Мексичка
    -0.69
    AutoScale
    -0.66
    StoryboardSegue
    -0.65
     transférez
    -0.60
     preſent
    -0.60
    }))
    -0.60
     BnF
    -0.59
     ब्रेकडाउन
    -0.57
    POSITIVE LOGITS
    лык
    0.47
    stris
    0.47
    عض
    0.44
    iny
    0.43
    twimg
    0.43
    §
    0.43
     Fund
    0.42
    ServiceClient
    0.42
     Anteil
    0.42
     fund
    0.41
    Activations Density 38.921%

    No Known Activations