© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15900
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to forestry, vegetation, and runoff

    oai_token-act-pair · gemini-2.0-flash

    forest

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Paglinawan
    -0.95
    __':
    -0.94
    __":
    -0.86
    __':
    -0.86
     Roskov
    -0.80
    __":
    -0.79
     تضيفلها
    -0.77
    Personendaten
    -0.73
     <>",
    -0.73
    Демографія
    -0.73
    POSITIVE LOGITS
    venty
    0.42
    κτή
    0.36
    мере
    0.36
    ¬
    0.35
    mer
    0.35
    ./
    0.34
    stead
    0.34
     cover
    0.34
     offering
    0.34
                                  
    0.33
    Activations Density 2.192%

    No Known Activations