© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7793
    Prev
    Next
    INDEX
    Explanations

    mentions of grass

    oai_token-act-pair · gemini-2.0-flash

    grass

    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
    ↵↵
    -1.06
    '
    -0.94
    ‘
    -0.89
    ↵
    -0.77
    <bos>
    -0.75
    ’
    -0.70
    {
    -0.67
    Firstly
    -0.63
     Firstly
    -0.61
    1
    -0.58
    POSITIVE LOGITS
    ."</
    0.84
    }{*}{
    0.82
    XmlAccessType
    0.76
    \}\\
    0.74
    ardless
    0.74
    __":
    0.73
    __)
    0.73
    IGraphics
    0.73
    Werde
    0.72
    .}(
    0.72
    Activations Density 1.711%

    No Known Activations