© 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. 11887
    Prev
    Next
    INDEX
    Explanations

    Portuguese words used in a programming context.

    oai_token-act-pair · gemini-2.0-flash

    code/technical text

    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
     상세
    -0.56
    awtextra
    -0.50
     /\.
    -0.50
    mab
    -0.49
    PRNewswire
    -0.48
    ̍
    -0.48
    eabouts
    -0.48
     treff
    -0.47
    msgSender
    -0.47
    ineno
    -0.46
    POSITIVE LOGITS
    BagConstraints
    0.60
     '\\;'
    0.59
     personalizados
    0.58
     personnalisées
    0.52
    AndroidJUnit
    0.52
    Kaynakça
    0.52
     tarvit
    0.51
     виправивши
    0.51
    ArrowToggle
    0.51
     personalizadas
    0.51
    Activations Density 0.204%

    No Known Activations