© 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. 13436
    Prev
    Next
    INDEX
    Explanations

    words relating to social happenings and events

    oai_token-act-pair · gemini-2.0-flash

    Code/proper nouns

    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
     $
    -0.57
     שוליים
    -0.57
    ########.
    -0.56
     Smarty
    -0.52
    ">'.$
    -0.52
     $\$
    -0.51
    ității
    -0.51
     BorderRadius
    -0.51
    ">$
    -0.49
    Diwedd
    -0.48
    POSITIVE LOGITS
    NameInMap
    0.57
    SourceChecksum
    0.56
    EndGlobalSection
    0.54
     Blanco
    0.50
    ForValue
    0.49
    Hispanic
    0.49
     lamang
    0.48
    EXTENSION
    0.47
     hispanic
    0.47
     оригіналу
    0.47
    Activations Density 44.245%

    No Known Activations