© 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. 1197
    Prev
    Next
    INDEX
    Explanations

    phrases about being honest and open about having a tough time

    oai_token-act-pair · gemini-2.0-flash

    website/advertising technical words

    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
     sort
    -0.77
    sort
    -0.70
     Sort
    -0.56
     sorted
    -0.55
    sorted
    -0.54
     épaules
    -0.54
    ValueGenerated
    -0.52
    Sort
    -0.51
     sorts
    -0.51
     hadapan
    -0.50
    POSITIVE LOGITS
    TagMode
    0.66
    IsContent
    0.66
     Baillargeon
    0.65
    "}")
    0.63
     Himo
    0.58
    ~*~
    0.54
    FTFY
    0.53
    numerusform
    0.52
    etron
    0.51
    cachor
    0.51
    Activations Density 10.105%

    No Known Activations