© 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. 8029
    Prev
    Next
    INDEX
    Explanations

    dates and numbers in different formats, often combined with surrounding text

    oai_token-act-pair · gemini-2.0-flash

    say ":"

    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
    httphttps
    -0.54
     continúas
    -0.53
     unknownFields
    -0.49
    setupUi
    -0.47
    IntoConstraints
    -0.47
    fieldId
    -0.46
    ग्री
    -0.44
    calaure
    -0.44
    ñores
    -0.44
    IVATE
    -0.43
    POSITIVE LOGITS
     :
    2.17
     ;
    1.70
     :}
    1.59
     :
    1.51
     :</
    1.38
     :\\
    1.23
     :'
    1.21
     :"
    1.20
     :",
    1.20
     :—
    1.17
    Activations Density 9.455%

    No Known Activations