© 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. 8468
    Prev
    Next
    INDEX
    Explanations

    quotes, what was said and who said it.

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    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
    CodeAttribute
    -0.74
    <bos>
    -0.64
    IUrlHelper
    -0.62
    Chham
    -0.60
    BeginInit
    -0.60
    OGND
    -0.58
    UDAD
    -0.58
    فته
    -0.57
    nextDouble
    -0.57
     ProtoMessage
    -0.57
    POSITIVE LOGITS
     createState
    0.47
    XtraGrid
    0.44
    successful
    0.40
     vicenda
    0.40
    guien
    0.40
     tapaht
    0.39
    ewon
    0.39
    mentação
    0.39
     Successful
    0.38
    DotNetBar
    0.38
    Activations Density 0.053%

    No Known Activations