© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6385
    Prev
    Next
    INDEX
    Explanations

    URLs and related markup.

    oai_token-act-pair · gemini-2.0-flash

    URLs and code

    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
    -0.88
     Roskov
    -0.81
    IntoConstraints
    -0.77
     StatefulWidget
    -0.77
     nahilalakip
    -0.76
     NgModule
    -0.76
     &___
    -0.75
    enumi
    -0.75
     GenerationType
    -0.74
    
    -0.74
    POSITIVE LOGITS
     وتسجيلات
    0.62
     <
    0.54
    </strong>
    0.52
    ),
    0.50
     (
    0.48
    <
    0.47
    /
    0.45
    ).
    0.45
    ↵↵
    0.45
    </sup>
    0.44
    Activations Density 6.033%

    No Known Activations