© 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. 12111
    Prev
    Next
    INDEX
    Explanations

    programming code and technical discussion.

    oai_token-act-pair · gemini-2.0-flash

    Computer threads

    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
     thread
    -2.47
     Thread
    -2.42
    Thread
    -2.27
     threads
    -2.22
    thread
    -2.20
     THREAD
    -2.17
     forum
    -2.02
    Forum
    -1.95
    Threads
    -1.94
     Forum
    -1.92
    POSITIVE LOGITS
     surla
    0.54
    watercolor
    0.50
     LCCN
    0.50
     Wikispecies
    0.50
    ppler
    0.48
     Picchu
    0.48
    FTAR
    0.47
     BoxFit
    0.46
    nonatomic
    0.45
     KISS
    0.45
    Activations Density 1.422%

    No Known Activations