© 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. 8554
    Prev
    Next
    INDEX
    Explanations

    titles like "director of corporate affairs" and "Vice President for Business"

    oai_token-act-pair · gemini-2.0-flash

    of, for

    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
    extAlignment
    -0.63
    Operation
    -0.54
     Operation
    -0.52
    InputTagHelper
    -0.50
     OPERATION
    -0.48
    OPERATION
    -0.48
    )}}{
    -0.47
    ียง
    -0.47
    bewerken
    -0.47
    ########.
    -0.46
    POSITIVE LOGITS
     بيها
    0.61
     EconPapers
    0.60
    исленность
    0.58
    ercito
    0.57
    BITDA
    0.57
    kirch
    0.56
     AssemblyCulture
    0.56
     Conscience
    0.56
     Winfield
    0.55
    ργ
    0.54
    Activations Density 5.379%

    No Known Activations