© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3754
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical or therapeutic settings and activities, as well as more general instances of health or wellbeing.

    oai_token-act-pair · gemini-2.0-flash

    health and difficult situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    DoubleQuotes
    -0.64
     дописавши
    -0.58
    rmtree
    -0.56
    RectangleBorder
    -0.54
    mtliche
    -0.51
    //</
    -0.50
    UnitTesting
    -0.50
    
    -0.50
     Afford
    -0.49
     defaultstate
    -0.49
    POSITIVE LOGITS
     tempore
    0.57
    ELTS
    0.55
    righted
    0.54
     relâche
    0.52
    PreferredItem
    0.51
    fromCharCode
    0.51
    Fernseh
    0.50
    PROC
    0.49
    assies
    0.49
    ัย
    0.49
    Activations Density 1.809%

    No Known Activations