© 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. 6390
    Prev
    Next
    INDEX
    Explanations

    the word "case" and words like "one" or "above" that often precede references to it

    oai_token-act-pair · gemini-2.0-flash

    case

    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
    ".
    -0.71
    ()")
    -0.62
    ()");
    -0.61
     Diſ
    -0.61
    PyErr
    -0.60
     ſche
    -0.59
     auffi
    -0.59
     Reſ
    -0.58
    ()',
    -0.57
    ()",
    -0.55
    POSITIVE LOGITS
     demais
    0.71
     doInBackground
    0.65
     CURIAM
    0.65
    WebVitals
    0.64
     vVar
    0.63
    GroupLayout
    0.62
    quiao
    0.60
    viper
    0.59
    первых
    0.58
     gynnwys
    0.57
    Activations Density 0.452%

    No Known Activations