© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15663
    Prev
    Next
    INDEX
    Explanations

    quotes and emphasized words in political contexts

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    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
    AddTagHelper
    -0.73
     <=",
    -0.71
    principalColumn
    -0.67
    MethodManager
    -0.60
     disgraced
    -0.58
     disgrace
    -0.57
    oué
    -0.57
    AnchorStyles
    -0.56
    awtextra
    -0.56
    acabana
    -0.56
    POSITIVE LOGITS
     extérieures
    0.60
    casus
    0.59
     complètes
    0.58
     particulières
    0.55
     pieza
    0.55
     privées
    0.52
     élevées
    0.51
     automatiques
    0.50
     foncé
    0.49
     vectorielles
    0.49
    Activations Density 5.662%

    No Known Activations