© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9085
    Prev
    Next
    INDEX
    Explanations

    mentions of documents, especially interviews, papers, episodes, or sections, and sometimes police

    oai_token-act-pair · gemini-2.0-flash

    news and legal reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    MENAFN
    -0.59
     médicaux
    -0.52
     autorytatywna
    -0.49
    XMLSchema
    -0.48
     veux
    -0.48
     préfère
    -0.47
     guantes
    -0.47
     culturelles
    -0.45
    }}^{\
    -0.44
     veut
    -0.43
    POSITIVE LOGITS
    expandindo
    0.69
    ModelSerializer
    0.64
    السكان
    0.55
    InBackground
    0.55
    utilisons
    0.54
    RetentionPolicy
    0.54
    lossians
    0.53
    styleType
    0.52
    Παραπομπές
    0.52
     eyel
    0.51
    Activations Density 0.595%

    No Known Activations