© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 763
    Prev
    Next
    INDEX
    Explanations

    words or phrases written in all capital letters

    oai_token-act-pair · gemini-2.0-flash

    say "uppercase suffixes" Method used: 2 — because the tokens after are consistently uppercase fragments, so "uppercase suffixes"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ly
    -0.43
    nt
    -0.40
    bes
    -0.38
    ges
    -0.38
    ukone
    -0.38
    ls
    -0.37
    ts
    -0.37
    ves
    -0.37
    bs
    -0.36
     سكانية
    -0.36
    POSITIVE LOGITS
     Económica
    0.52
     enfans
    0.51
     vectorielles
    0.49
     religieuses
    0.47
     purpoſe
    0.47
     termica
    0.46
     Universitaria
    0.45
     vectorielle
    0.45
    DBA
    0.44
     industriels
    0.44
    Activations Density 20.797%

    No Known Activations