© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9824
    Prev
    Next
    INDEX
    Explanations

    code documentation blocks

    oai_token-act-pair · gemini-2.0-flash

    Configuration options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    DockStyle
    -1.01
    AsUp
    -0.94
    complexContent
    -0.88
    LLocation
    -0.85
    NewUrlParser
    -0.80
     snippetHide
    -0.79
    ItemBackground
    -0.77
    TintMode
    -0.75
    UserScript
    -0.74
    */),
    -0.71
    POSITIVE LOGITS
    </strong>
    0.45
    msgSender
    0.45
     D
    0.44
     L
    0.44
     sp
    0.43
     $
    0.43
    <eos>
    0.43
     "
    0.42
     b
    0.41
    logger
    0.40
    Activations Density 2.610%

    No Known Activations