© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12832
    Prev
    Next
    INDEX
    Explanations

    descriptions of events, especially ones that are annual

    oai_token-act-pair · gemini-2.0-flash

    technical/report text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Narayan
    -0.49
    hole
    -0.48
     calling
    -0.45
     Dickerson
    -0.44
    География
    -0.44
    ++]=
    -0.43
    řské
    -0.42
    Démographie
    -0.42
     microstructure
    -0.42
     hội
    -0.41
    POSITIVE LOGITS
     pinulongan
    0.78
     propOrder
    0.65
    XmlType
    0.65
     doInBackground
    0.64
    UnusedPrivate
    0.63
    AccessorTable
    0.63
    InSection
    0.60
    sidemargin
    0.60
    LLocation
    0.60
    ंदीखरीदारी
    0.59
    Activations Density 1.186%

    No Known Activations