© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    words relating to personal protective equipment and medical items

    oai_token-act-pair · gemini-2.0-flash

    protection and prevention

    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
    <bos>
    -0.56
    bių
    -0.54
    ApiOperation
    -0.54
    iosync
    -0.50
    bės
    -0.48
    ISTICS
    -0.47
     resourceCulture
    -0.47
     Ouverture
    -0.47
    ิด
    -0.46
     оригіналу
    -0.46
    POSITIVE LOGITS
    PyExc
    0.70
     BoxFit
    0.68
     يتيمه
    0.62
     nahilalakip
    0.58
    AutoField
    0.55
    Obrázky
    0.54
    XmlAccessType
    0.54
     InputDecoration
    0.53
    脚注の使い方
    0.52
     endfor
    0.51
    Activations Density 0.731%

    No Known Activations