© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11743
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly years, section titles, and IDs, especially in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    Section numbering

    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
     is
    -0.60
     has
    -0.53
     was
    -0.53
     does
    -0.46
    </i>
    -0.46
    has
    -0.46
    </em>
    -0.46
     will
    -0.45
    ()");
    -0.45
     might
    -0.45
    POSITIVE LOGITS
    SharedDtor
    0.92
    Lähteet
    0.77
    WebElementEntity
    0.72
    ########.
    0.71
     kasarigan
    0.65
     EClass
    0.65
     createState
    0.64
    Vidite
    0.64
     Administrativna
    0.63
     CONTENTS
    0.62
    Activations Density 29.515%

    No Known Activations