© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6585
    Prev
    Next
    INDEX
    Explanations

    verbs, especially present tense or past tense participial forms

    oai_token-act-pair · gemini-2.0-flash

    pluralized or verb forms ending in 'es', 'ates', or 's'

    np_token-act-pair-logits · gpt-4o-mini

    verb endings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AddTagHelper
    -0.96
    
    -0.83
     MainAxisSize
    -0.76
     defaultstate
    -0.72
     насеље
    -0.71
    .*")]
    -0.70
     يتيمه
    -0.65
     povezave
    -0.64
    
    -0.63
    ioutil
    -0.62
    POSITIVE LOGITS
    es
    0.98
    ates
    0.97
    ens
    0.91
    tains
    0.89
    ves
    0.87
    zes
    0.86
    ses
    0.85
    ulates
    0.82
    ises
    0.81
    izes
    0.81
    Activations Density 2.478%

    No Known Activations