© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7313
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to be identifying text from quotations specifically about slavery, freedom, and work

    oai_token-act-pair · 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
     Kontext
    -0.49
    DockStyle
    -0.46
    loài
    -0.45
    obox
    -0.43
    __;
    -0.43
    brenner
    -0.43
    ustainable
    -0.41
    venues
    -0.41
     prestations
    -0.41
     صوتيه
    -0.41
    POSITIVE LOGITS
     unknownFields
    0.62
     ClassNotFound
    0.57
     ThemeData
    0.56
    бият
    0.56
    Weird
    0.54
    makeatletter
    0.54
    icitis
    0.53
     nakalista
    0.53
    جوايز
    0.53
    اعة
    0.53
    Activations Density 0.989%

    No Known Activations