© 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. 11556
    Prev
    Next
    INDEX
    Explanations

    words and phrases that predict the future state of something

    oai_token-act-pair · 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
     remained
    -1.78
     persisted
    -1.50
     remain
    -1.50
     retained
    -1.48
     continued
    -1.48
     stayed
    -1.48
     remaining
    -1.44
     stays
    -1.43
     staying
    -1.42
     perman
    -1.41
    POSITIVE LOGITS
    paramref
    0.58
    ElementException
    0.57
    PickerController
    0.56
     oprot
    0.54
     تضيفلها
    0.53
    ImageContext
    0.51
    ovascular
    0.50
    évaluateur
    0.49
     tassels
    0.48
     alphabetically
    0.48
    Activations Density 1.356%

    No Known Activations