© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9878
    Prev
    Next
    INDEX
    Explanations

    phrases that are questions or commands

    oai_token-act-pair · gemini-2.0-flash

    Okay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    BeginInit
    -0.53
     therefore
    -0.52
    beqa
    -0.45
     hence
    -0.43
    sequently
    -0.43
    beni
    -0.41
    imov
    -0.40
     Bande
    -0.40
    thon
    -0.40
    letics
    -0.40
    POSITIVE LOGITS
    новништво
    0.73
     betweenstory
    0.65
    webElementXpaths
    0.65
    цездатний
    0.63
    setResult
    0.63
    "}"
    0.63
     ddelweddau
    0.62
     gynhyrchwyd
    0.62
     autorytatywna
    0.62
     NSCoder
    0.61
    Activations Density 2.108%

    No Known Activations