© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14944
    Prev
    Next
    INDEX
    Explanations

    email or code snippets with arrows and annotations

    oai_token-act-pair · gemini-2.0-flash

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     betweenstory
    -0.88
     autorytatywna
    -0.76
     GenerationType
    -0.67
     <=",
    -0.64
    ⓧ
    -0.62
     desac
    -0.62
     nakalista
    -0.62
    
    -0.60
    )*/
    -0.60
    =?";
    -0.59
    POSITIVE LOGITS
    doubleValue
    0.47
    I
    0.47
    Regards
    0.47
     I
    0.46
    ess
    0.45
    DllImport
    0.45
     Ben
    0.43
     etc
    0.43
     [
    0.43
     prensa
    0.43
    Activations Density 1.913%

    No Known Activations