© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12831
    Prev
    Next
    INDEX
    Explanations

    words that express an intention or a goal

    oai_token-act-pair · gemini-2.0-flash

    methods and processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     médicaux
    -0.68
     actuels
    -0.67
     للمعارف
    -0.66
     mourut
    -0.65
     définiti
    -0.65
     ExecuteAsync
    -0.63
     geïsole
    -0.63
     fermés
    -0.62
    พาะ
    -0.61
     régionales
    -0.61
    POSITIVE LOGITS
     trace
    0.77
     stand
    0.75
     progress
    0.74
     measure
    0.72
     train
    0.72
     form
    0.71
     line
    0.70
     fall
    0.70
     cover
    0.69
     track
    0.69
    Activations Density 14.601%

    No Known Activations