© 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. 5230
    Prev
    Next
    INDEX
    Explanations

    German sentences with a discussion of how to write them

    oai_token-act-pair · gemini-2.0-flash

    Computer code and foreign languages

    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
    WebVitals
    -0.81
    SequentialGroup
    -0.80
    enumi
    -0.79
    ImageContext
    -0.79
    setVerticalGroup
    -0.78
    GraphicsUnit
    -0.75
    webElementXpaths
    -0.75
    bootstrapcdn
    -0.72
     resourceCulture
    -0.71
     newBuilder
    -0.71
    POSITIVE LOGITS
    msford
    0.53
    Malley
    0.48
    Barr
    0.46
    WithTag
    0.45
     Briefly
    0.44
    IVIA
    0.43
    thel
    0.43
     cep
    0.43
    веси
    0.42
    Shack
    0.42
    Activations Density 0.708%

    No Known Activations