© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2496
    Prev
    Next
    INDEX
    Explanations

    common words or phrases and short verbs, especially "to be" verbs, adjectives, and some nouns.

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    seem
    -0.73
     >=",
    -0.71
     seeming
    -0.65
     seem
    -0.63
    Seems
    -0.60
     semblent
    -0.59
     Seems
    -0.58
    featureID
    -0.58
     kasarigan
    -0.57
    
    -0.57
    POSITIVE LOGITS
    msgTypes
    0.52
    nutie
    0.49
    ιού
    0.45
     Gouverneur
    0.45
    wicket
    0.44
     UIKit
    0.44
    <bos>
    0.44
    spaceBetween
    0.43
    جوايز
    0.43
     обо
    0.42
    Activations Density 22.706%

    No Known Activations