© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11366
    Prev
    Next
    INDEX
    Explanations

    snippets of code or text discussing code

    oai_token-act-pair · gemini-2.0-flash

    code context

    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
    Према
    -0.66
     Dä
    -0.51
    ROK
    -0.50
     neutre
    -0.47
    ThroughAttribute
    -0.47
    Featured
    -0.46
     africains
    -0.46
     makl
    -0.45
    rok
    -0.44
    nist
    -0.44
    POSITIVE LOGITS
    StoryboardSegue
    0.79
    بوابة
    0.74
    MLLoader
    0.63
    AutoField
    0.59
    parsedMessage
    0.59
     Balfour
    0.57
    पया
    0.57
     Reverso
    0.56
     FetchType
    0.56
    AddTagHelper
    0.55
    Activations Density 3.343%

    No Known Activations