© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12766
    Prev
    Next
    INDEX
    Explanations

    content regarding slavery

    oai_token-act-pair · gemini-2.0-flash

    slavery, ownership

    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
     Owners
    -2.84
     Owner
    -2.78
     owners
    -2.70
     owner
    -2.69
     ownership
    -2.67
    Owners
    -2.61
    Owner
    -2.59
    owner
    -2.56
     Ownership
    -2.56
    owners
    -2.55
    POSITIVE LOGITS
     '/';
    0.43
     co
    0.42
    虑
    0.41
    CodeAttribute
    0.41
    Ligações
    0.39
     tháng
    0.38
    snprintf
    0.38
    Jeografia
    0.35
     zvuky
    0.35
    cabul
    0.35
    Activations Density 1.655%

    No Known Activations