© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1384
    Prev
    Next
    INDEX
    Explanations

    words and phrases in subjective narratives that describe the causal chain of events, and feelings of injustice and harm

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    GEBURTSDATUM
    -0.54
     Hopf
    -0.50
    tät
    -0.48
    Abit
    -0.48
     Hym
    -0.47
     AssemblyCulture
    -0.46
    nonatomic
    -0.46
    wijs
    -0.45
    forChild
    -0.45
    resave
    -0.44
    POSITIVE LOGITS
    Composição
    0.69
     Waterhouse
    0.68
     Pemberton
    0.67
    Magdalena
    0.67
     concentration
    0.66
     concentra
    0.66
    veloppement
    0.65
    Caractéristiques
    0.65
     practition
    0.65
    CARACTERIST
    0.65
    Activations Density 1.820%

    No Known Activations