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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11072
    Prev
    Next
    INDEX
    Explanations

    words associated with a college newspaper

    oai_token-act-pair · gemini-2.0-flash

    page

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    tvguidetime
    -0.68
    出版年
    -0.67
     MainAxisSize
    -0.66
    MENAFN
    -0.61
    
    -0.59
    Personendaten
    -0.59
     للمعارف
    -0.54
     WaitForSeconds
    -0.53
    PMID
    -0.53
    ponses
    -0.52
    POSITIVE LOGITS
    <bos>
    0.57
    oriques
    0.55
    országban
    0.55
    ERÍA
    0.50
    UnsafeEnabled
    0.47
    iors
    0.47
    ORIAL
    0.47
     opér
    0.45
    χε
    0.45
    ędzynarod
    0.45
    Activations Density 0.323%

    No Known Activations