© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10528
    Prev
    Next
    INDEX
    Explanations

    quotes and related attribution

    oai_token-act-pair · gemini-2.0-flash

    quotes or statements from sources

    np_token-act-pair-logits · gpt-4o-mini

    quote symbol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     المعيارى
    -1.00
     GenerationType
    -0.99
     autorytatywna
    -0.96
     Италијани
    -0.95
    tagext
    -0.89
    OGND
    -0.85
    sizeCache
    -0.85
     estekak
    -0.84
     betweenstory
    -0.84
     فريبيس
    -0.83
    POSITIVE LOGITS
    then
    0.48
     then
    0.48
     R
    0.47
    ENCE
    0.44
    </h3>
    0.44
     (
    0.44
    imp
    0.42
    </b>
    0.42
    omin
    0.42
    all
    0.41
    Activations Density 0.577%

    No Known Activations