© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10062
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express a judgment, opinion, or qualification.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     autorytatywna
    -0.69
    DropColumn
    -0.55
    CreateMap
    -0.53
    fromnode
    -0.52
     oars
    -0.51
    Misión
    -0.50
     Falken
    -0.50
    Buongiorno
    -0.49
     testified
    -0.49
    kegaard
    -0.49
    POSITIVE LOGITS
    <bos>
    0.96
    MessageTagHelper
    0.69
     preocupes
    0.59
    enderror
    0.58
    setopt
    0.57
    //
    0.57
    évaluateur
    0.57
    цион
    0.56
     így
    0.54
    /*
    0.53
    Activations Density 1.226%

    No Known Activations