© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13661
    Prev
    Next
    INDEX
    Explanations

    statistics, especially numbers relating to sports scores and records

    oai_token-act-pair · gemini-2.0-flash

    tokens related to statistics or numerical data

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

    Sports statistics

    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
    WireFormatLite
    -0.74
    ativement
    -0.63
    WriteAttribute
    -0.60
    AndEndTag
    -0.59
    ValueStyle
    -0.57
    RTLD
    -0.56
    reactstrap
    -0.56
    GOTREF
    -0.56
     ✭✭
    -0.56
     CreateTagHelper
    -0.55
    POSITIVE LOGITS
    homonymie
    0.62
    ThroughAttribute
    0.61
    Sucesor
    0.60
     hundreds
    0.55
    */;
    0.53
     thousands
    0.51
    vast
    0.49
    UnusedPrivate
    0.48
    )");
    0.48
    здрав
    0.47
    Activations Density 1.230%

    No Known Activations