© 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. 8883
    Prev
    Next
    INDEX
    Explanations

    the word "more"

    oai_token-act-pair · gemini-2.0-flash

    more/less

    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
     than
    -1.71
     niż
    -1.12
     THAN
    -1.01
     kuin
    -1.00
    Than
    -1.00
     än
    -0.98
    than
    -0.90
     než
    -0.82
    THAN
    -0.79
     Than
    -0.74
    POSITIVE LOGITS
     then
    1.48
    then
    1.34
    Then
    1.17
     Then
    1.09
     THEN
    0.92
    THEN
    0.92
    ówczas
    0.75
     puis
    0.73
     dann
    0.71
     lalu
    0.71
    Activations Density 0.864%

    No Known Activations