© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1772
    Prev
    Next
    INDEX
    Explanations

    both the beginning and middle of the saying "if it walks like a duck, quacks like a duck, looks like a duck..." or mentions of Emperors

    oai_token-act-pair · gemini-2.0-flash

    Actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    enumii
    -0.86
     contextLoads
    -0.82
    CloseOperation
    -0.81
    Previews
    -0.80
    expandindo
    -0.77
     تانيه
    -0.77
    AndroidJUnit
    -0.74
    ()]);
    -0.73
     Савезне
    -0.73
    UnusedPrivate
    -0.72
    POSITIVE LOGITS
     do
    0.51
     drink
    0.50
     eating
    0.49
     drinking
    0.48
     swim
    0.47
     reading
    0.47
     dress
    0.47
     menstru
    0.46
    drink
    0.46
     eaters
    0.43
    Activations Density 1.368%

    No Known Activations