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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6547
    Prev
    Next
    INDEX
    Explanations

    named entities alone or alongside titles, as well as some words that start with capital letters and/or are short.

    oai_token-act-pair · gemini-2.0-flash

    Prepositions

    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
     mauvaises
    -0.76
     enfans
    -0.72
     démocr
    -0.71
     étoient
    -0.69
     dépenses
    -0.68
     pertes
    -0.68
     vícti
    -0.68
     renseignements
    -0.67
     pouvoirs
    -0.66
     aveug
    -0.66
    POSITIVE LOGITS
     as
    1.32
     after
    1.16
     across
    1.15
     before
    1.15
     throughout
    1.14
     within
    1.09
     with
    1.06
     beyond
    1.04
     through
    1.03
     around
    1.03
    Activations Density 14.447%

    No Known Activations