© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6098
    Prev
    Next
    INDEX
    Explanations

    the stem "cur" used in different words

    oai_token-act-pair · gemini-2.0-flash

    cur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     dna
    -0.75
     PKK
    -0.71
    yakarta
    -0.71
    JAXB
    -0.70
     Nagasaki
    -0.70
     Vallarta
    -0.69
     joker
    -0.69
     Protestantism
    -0.69
    ρους
    -0.69
    gdx
    -0.68
    POSITIVE LOGITS
    WithIOException
    0.70
    mergeFrom
    0.57
    esterday
    0.56
    hellip
    0.56
     فريبيس
    0.55
    studded
    0.53
    klart
    0.53
     ProtoMessage
    0.51
     these
    0.50
    Билгалдахарш
    0.50
    Activations Density 0.552%

    No Known Activations