© 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. 3363
    Prev
    Next
    INDEX
    Explanations

    HTML code and associated tags/elements

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    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
    ⓧ
    -0.83
    WithIOException
    -0.75
    UnsafeEnabled
    -0.71
    FontOfSize
    -0.71
    (||
    -0.71
     оригіналу
    -0.69
    StoryboardSegue
    -0.69
    Diwedd
    -0.68
    ISupport
    -0.66
    ValueStyle
    -0.66
    POSITIVE LOGITS
     Pim
    0.37
    kit
    0.35
    Implicit
    0.35
    shop
    0.34
     TÉCN
    0.33
     nôtre
    0.33
     bloodstream
    0.33
    depend
    0.32
    ષ
    0.32
    sys
    0.32
    Activations Density 0.717%

    No Known Activations