© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13266
    Prev
    Next
    INDEX
    Explanations

    text where medical treatment of patients is being described

    oai_token-act-pair · gemini-2.0-flash

    scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Composable
    -0.52
     Mada
    -0.49
    PhysRevD
    -0.49
     Bandar
    -0.47
     injection
    -0.46
    ServletConfig
    -0.46
     Chancery
    -0.45
     grund
    -0.45
     разве
    -0.44
    Попис
    -0.44
    POSITIVE LOGITS
    
    0.66
    ValueStyle
    0.65
    Tikang
    0.57
     متعلقه
    0.56
     كومونز
    0.55
    PutMapping
    0.55
    zzleHttp
    0.53
    publicain
    0.52
    hiana
    0.52
     estimés
    0.52
    Activations Density 5.030%

    No Known Activations