© 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. 5273
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" preceded by other words and phrases such as “committed"

    oai_token-act-pair · gemini-2.0-flash

    Action verbs

    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
    SharedDtor
    -0.64
     Савезне
    -0.61
    зулта
    -0.60
    AndEndTag
    -0.60
    <?
    -0.60
     Administrativna
    -0.59
     umgeben
    -0.57
    Демографія
    -0.57
    Begriffsklä
    -0.55
     незавершена
    -0.54
    POSITIVE LOGITS
     calculate
    0.93
     consume
    0.90
     apply
    0.89
     undergo
    0.89
     classify
    0.88
     characterize
    0.87
     evaluate
    0.85
     define
    0.85
     describe
    0.84
     celebrate
    0.84
    Activations Density 6.320%

    No Known Activations