© 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. 14704
    Prev
    Next
    INDEX
    Explanations

    some words in Russian and Arabic

    oai_token-act-pair · gemini-2.0-flash

    non-English languages

    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
    s
    -1.08
    se
    -1.02
    g
    -1.01
    v
    -1.00
    te
    -0.99
    a
    -0.98
    u
    -0.98
    e
    -0.98
    so
    -0.97
    m
    -0.96
    POSITIVE LOGITS
    contentLoaded
    0.70
     gynhyrchwyd
    0.70
    iffance
    0.68
    ]='\
    0.60
     "..\..\..\
    0.56
     otomatig
    0.56
     Мексичка
    0.55
    namefont
    0.54
    ftance
    0.54
     Италијани
    0.52
    Activations Density 1.922%

    No Known Activations