© 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. 15954
    Prev
    Next
    INDEX
    Explanations

    names starting with "Mc"

    oai_token-act-pair · gemini-2.0-flash

    "Mc" names

    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
    èze
    -0.58
    κλη
    -0.50
    ступ
    -0.50
    dega
    -0.50
    getElements
    -0.48
    dfs
    -0.47
    colgroup
    -0.47
    èdia
    -0.46
    urie
    -0.46
    isle
    -0.46
    POSITIVE LOGITS
     Offisielt
    0.74
    ArrowToggle
    0.65
    antaranya
    0.65
     InputDecoration
    0.65
     للمعارف
    0.61
     Jefus
    0.61
     Италијани
    0.60
    featureID
    0.60
    viembre
    0.59
     onlyOwner
    0.59
    Activations Density 0.237%

    No Known Activations