© 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. 6670
    Prev
    Next
    INDEX
    Explanations

    words related to commerce and events

    oai_token-act-pair · gemini-2.0-flash

    scheduling

    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
    URLException
    -0.70
    Geplaatst
    -0.58
    JspWriter
    -0.57
     Vikipedi
    -0.57
     totalSupply
    -0.53
     OMITBAD
    -0.50
    XmlAccessorType
    -0.50
     disponibilités
    -0.49
    resave
    -0.49
     esternos
    -0.48
    POSITIVE LOGITS
    substack
    0.59
     Cottage
    0.53
    Lago
    0.52
    Persön
    0.51
    ømme
    0.49
    iens
    0.49
    ClientSize
    0.49
    دانشنامهٔ
    0.48
    FieldNumber
    0.47
     rè
    0.47
    Activations Density 4.652%

    No Known Activations