© 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. 13837
    Prev
    Next
    INDEX
    Explanations

    words or phrases that refer to something mentioned previously in the text

    oai_token-act-pair · gemini-2.0-flash

    referring to other text

    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
     succinctly
    -0.56
     duidelijk
    -0.52
     concise
    -0.49
     retrospect
    -0.48
     BoxFit
    -0.47
     Punct
    -0.46
     cremation
    -0.46
     प्रद
    -0.46
     paragon
    -0.46
    MethodManager
    -0.46
    POSITIVE LOGITS
    WriteTagHelper
    0.64
    oredCriteria
    0.63
    transQ
    0.61
     utafitiHapana
    0.59
    /*
    0.54
    MessageOf
    0.53
     виправивши
    0.53
    
    0.52
    ReusableCell
    0.52
    featureID
    0.51
    Activations Density 2.728%

    No Known Activations