© 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. 12620
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers which likely represent references and footnotes

    oai_token-act-pair · gemini-2.0-flash

    bracket

    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
    1
    -0.77
    2
    -0.77
    8
    -0.69
    5
    -0.68
    :
    -0.68
    3
    -0.67
    [
    -0.67
    7
    -0.67
    9
    -0.66
    4
    -0.65
    POSITIVE LOGITS
    SourceChecksum
    1.09
    Autoritní
    1.02
    TargetException
    0.96
    tagHelperRunner
    0.92
     Савезне
    0.91
     saites
    0.87
    featureID
    0.86
     Efq
    0.85
    PreferredItem
    0.84
     Portail
    0.83
    Activations Density 1.646%

    No Known Activations