© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15431
    Prev
    Next
    INDEX
    Explanations

    the word "published" or "publication" (or similar term)

    oai_token-act-pair · gemini-2.0-flash

    published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     commerciali
    -0.82
     varandra
    -0.72
     urbanas
    -0.65
     vettor
    -0.63
     automatiques
    -0.63
     économiques
    -0.63
     själva
    -0.59
     popolari
    -0.59
     financières
    -0.59
    ConstraintMaker
    -0.58
    POSITIVE LOGITS
    utilisons
    0.81
    imanapun
    0.79
     Giud
    0.78
     ProtoMessage
    0.77
    riwal
    0.77
    requipa
    0.76
    Попис
    0.76
    menistan
    0.76
    Vidite
    0.75
     cdti
    0.75
    Activations Density 1.954%

    No Known Activations