© 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. 1356
    Prev
    Next
    INDEX
    Explanations

    LaTeX or some related markup.

    oai_token-act-pair · gemini-2.0-flash

    LaTeX formatting

    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
    WidgetItem
    -0.61
    InstrumentedTest
    -0.58
     Shakira
    -0.58
    BagLayout
    -0.57
    rungsseite
    -0.55
    ondheim
    -0.54
    ioneers
    -0.54
    께
    -0.54
     Mishra
    -0.54
     blinks
    -0.53
    POSITIVE LOGITS
    ритори
    0.55
    UnusedPrivate
    0.51
    -}
    0.51
     fieldNum
    0.48
    -
    0.47
     {:.
    0.45
     veckor
    0.45
     }}^{
    0.44
     }}{
    0.43
     +,
    0.43
    Activations Density 8.064%

    No Known Activations