© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5509
    Prev
    Next
    INDEX
    Explanations

    a variety of named entities, with a political bent: people, places, governmental things

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     propOrder
    -0.81
    Попис
    -0.67
     CURIAM
    -0.66
     Efq
    -0.65
    __*/
    -0.63
     Италијани
    -0.62
    RTLD
    -0.61
    mapStateToProps
    -0.60
     MonoBehaviour
    -0.60
    emény
    -0.60
    POSITIVE LOGITS
     remain
    0.69
     never
    0.65
     remains
    0.64
     has
    0.63
     still
    0.60
     remained
    0.60
    이
    0.58
     became
    0.57
     becomes
    0.57
    가
    0.57
    Activations Density 7.003%

    No Known Activations