© 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. 784
    Prev
    Next
    INDEX
    Explanations

    abstract nouns related to narrative tension or plot.

    oai_token-act-pair · gemini-2.0-flash

    interest

    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
     tick
    -0.61
     ticked
    -0.59
     cross
    -0.56
     crossed
    -0.54
     Obituary
    -0.54
    cross
    -0.52
    ::_('
    -0.52
    providedIn
    -0.51
     Cross
    -0.50
    Obituary
    -0.50
    POSITIVE LOGITS
     interest
    1.03
     Interest
    0.98
    interest
    0.92
     INTEREST
    0.91
    Interest
    0.89
    INTEREST
    0.83
     interested
    0.78
     excitement
    0.77
     Interested
    0.75
    interested
    0.75
    Activations Density 0.730%

    No Known Activations