© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11895
    Prev
    Next
    INDEX
    Explanations

    statistics and facts that would be reported about sports or trading.

    oai_token-act-pair · gemini-2.0-flash

    Sports/football context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    addCriterion
    -0.68
    oredCriteria
    -0.59
    classID
    -0.56
     behoort
    -0.56
    ortium
    -0.55
    GMENT
    -0.54
    fjspx
    -0.54
    دانشنامهٔ
    -0.52
    ñales
    -0.49
    wikidata
    -0.49
    POSITIVE LOGITS
    存于互联网档案馆
    0.58
     iconLine
    0.52
    спонд
    0.52
    TRIBUN
    0.51
    ModelMap
    0.50
     Loa
    0.49
    礒
    0.49
    Portail
    0.49
    InjectAttribute
    0.46
    DebuggerStep
    0.46
    Activations Density 0.761%

    No Known Activations