© 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. 5425
    Prev
    Next
    INDEX
    Explanations

    C++ code

    oai_token-act-pair · gemini-2.0-flash

    1 or 2

    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
     esternos
    -1.17
     resourceCulture
    -1.05
    ViewFeatures
    -0.85
    ".
    -0.85
     oprot
    -0.83
    numerusform
    -0.82
    '],
    -0.82
    "),
    -0.82
    "],
    -0.81
    "]);
    -0.80
    POSITIVE LOGITS
    ,
    0.53
    iseite
    0.49
     
    0.47
     L
    0.47
    ;
    0.47
    /
    0.46
    *
    0.44
    L
    0.43
    :
    0.43
    &
    0.42
    Activations Density 5.266%

    No Known Activations