© 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. 5129
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people, especially with emotional context.

    oai_token-act-pair · gemini-2.0-flash

    people's activities

    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
    StoryboardSegue
    -0.69
    EndProject
    -0.68
    
    -0.56
    WebVitals
    -0.50
    ."));
    -0.50
    ']))
    -0.49
    Fell
    -0.49
     Fell
    -0.48
    hoeddwyd
    -0.48
    gonic
    -0.47
    POSITIVE LOGITS
     noqa
    0.68
    KommentareTeilen
    0.65
     used
    0.64
     supported
    0.59
     served
    0.57
     ProtoMessage
    0.56
     maintained
    0.56
    basicConfig
    0.55
     &___
    0.55
     enjoyed
    0.55
    Activations Density 1.048%

    No Known Activations