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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3889
    Prev
    Next
    INDEX
    Explanations

    Chinese and code-related terms, possibly related to dictionary compilation or UTF encoding

    oai_token-act-pair · gemini-2.0-flash

    coded text

    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
     abstrato
    -0.75
     quæ
    -0.74
     dedans
    -0.69
     économies
    -0.68
     cæ
    -0.68
     épais
    -0.68
     ſtate
    -0.65
     houſe
    -0.65
    ftance
    -0.65
    entibus
    -0.65
    POSITIVE LOGITS
     esternos
    0.68
    BeginContext
    0.66
    ValueStyle
    0.65
    ogaster
    0.64
    MLLoader
    0.64
    TemporalType
    0.63
    aryen
    0.63
    CloseOperation
    0.62
     disponibilités
    0.61
    RegressionTest
    0.60
    Activations Density 0.541%

    No Known Activations