© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5412
    Prev
    Next
    INDEX
    Explanations

    references to amounts of something, possibly in the context of a purchase or something happening to the subject.

    oai_token-act-pair · gemini-2.0-flash

    the presence of the substring 'em'

    np_token-act-pair-logits · gpt-4o-mini

    say "them"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    enderror
    -0.84
     '\\;'
    -0.79
     disambiguazione
    -0.79
    LookAnd
    -0.78
     Réponses
    -0.73
    setupUi
    -0.73
    ########.
    -0.71
    RegressionTest
    -0.67
     disponibilités
    -0.67
    Rohy
    -0.67
    POSITIVE LOGITS
     em
    2.20
    em
    1.82
    Em
    1.66
     Em
    1.61
     EM
    1.34
    EM
    1.30
     ’
    1.15
    emm
    0.92
     them
    0.90
     emm
    0.89
    Activations Density 0.949%

    No Known Activations