© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7209
    Prev
    Next
    INDEX
    Explanations

    a mix of pronouns, possessives, and the odd single quote

    oai_token-act-pair · gemini-2.0-flash

    ‘

    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
    bolistas
    -0.54
     Corintios
    -0.52
    Espèce
    -0.51
     GenerationType
    -0.51
     htons
    -0.49
     الاطلاع
    -0.48
     isInitialized
    -0.47
    encodeWith
    -0.47
     bbs
    -0.46
    InSection
    -0.45
    POSITIVE LOGITS
    windowFixed
    0.69
    Personendaten
    0.65
     over
    0.61
     continúas
    0.60
    ########.
    0.60
     per
    0.60
    per
    0.58
     cherchés
    0.56
    💼
    0.54
    ंदीखरीदारी
    0.50
    Activations Density 0.109%

    No Known Activations