© 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. 13140
    Prev
    Next
    INDEX
    Explanations

    a variety of political language and medical terms, possibly indicating an interest in rhetoric and debate related to health or current events.

    oai_token-act-pair · gemini-2.0-flash

    quoted speech

    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
    Whilst
    -0.74
     Whilst
    -0.70
     whilst
    -0.66
     mobilisation
    -0.64
     programmes
    -0.63
     Programmes
    -0.62
    itisation
    -0.61
     initialise
    -0.59
    liosis
    -0.59
     privatisation
    -0.59
    POSITIVE LOGITS
    PLES
    0.61
     =>
    0.60
     חיצוניים
    0.57
    €”
    0.56
     lenker
    0.56
    +#+#
    0.54
     kila
    0.53
    Feder
    0.53
     Feder
    0.52
    eabouts
    0.52
    Activations Density 5.104%

    No Known Activations