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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 987
    Prev
    Next
    INDEX
    Explanations

    the partial word "Ste"

    oai_token-act-pair · gemini-2.0-flash

    Ste

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ArrowToggle
    -0.60
    ArgsConstructor
    -0.54
     jadx
    -0.52
    цездатний
    -0.51
     ste
    -0.51
    ANTLR
    -0.51
     autorytatywna
    -0.50
     referenties
    -0.50
    зулта
    -0.48
     Ste
    -0.47
    POSITIVE LOGITS
    ագրություններ
    0.62
    expandindo
    0.60
    脚注の使い方
    0.54
     églises
    0.50
    infeld
    0.49
    enumi
    0.48
    ubakar
    0.48
     cref
    0.47
    ignées
    0.47
    gatsby
    0.47
    Activations Density 4.559%

    No Known Activations