© 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. 1762
    Prev
    Next
    INDEX
    Explanations

    the word "The" at the beginning of sentences or phrases

    oai_token-act-pair · gemini-2.0-flash

    The

    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
     the
    -0.60
    tagHelperRunner
    -0.56
    Véxase
    -0.55
     EconPapers
    -0.54
    parsedMessage
    -0.53
    PyExc
    -0.53
    Dtor
    -0.51
     Gual
    -0.51
    #+#
    -0.51
    ImageContext
    -0.50
    POSITIVE LOGITS
    a
    0.55
     sanitaires
    0.54
     financieras
    0.51
     escuchadas
    0.50
     connexe
    0.50
     kasarigan
    0.50
     artificiales
    0.49
    ś
    0.49
     consultato
    0.48
    permitAll
    0.48
    Activations Density 6.138%

    No Known Activations