© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9883
    Prev
    Next
    INDEX
    Explanations

    accounts of human rights abuses

    oai_token-act-pair · gemini-2.0-flash

    Human rights violations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     nahilalakip
    -0.82
     ujednoznacz
    -0.81
    ContentAlignment
    -0.69
    ----</
    -0.69
    EDEFAULT
    -0.69
    GEBURTSDATUM
    -0.67
    verwijspagina
    -0.66
    titleMargin
    -0.66
    memoized
    -0.65
    ThroughAttribute
    -0.64
    POSITIVE LOGITS
     JADX
    0.47
    вра
    0.46
    )?;
    0.45
    ftances
    0.45
    resaid
    0.44
     Audiodateien
    0.44
     sə
    0.43
    موقع
    0.43
    THISDAY
    0.43
    ทาง
    0.43
    Activations Density 3.848%

    No Known Activations