© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8110
    Prev
    Next
    INDEX
    Explanations

    the word "establish" and its variants

    oai_token-act-pair · gemini-2.0-flash

    establish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    extAlignment
    -1.38
     متعلقه
    -1.32
    contentLoaded
    -1.30
     autorytatywna
    -1.29
    Geplaatst
    -1.27
     InputDecoration
    -1.25
     nakalista
    -1.20
     nahilalakip
    -1.20
    NUMX
    -1.20
     CreateTagHelper
    -1.20
    POSITIVE LOGITS
    ↵
    1.67
    ↵↵
    1.51
    ↵↵↵
    1.02
    <eos>
    0.96
    ↵↵↵↵
    0.73
    .
    0.72
    for
    0.69
    e
    0.65
    in
    0.65
    and
    0.61
    Activations Density 1.105%

    No Known Activations