© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15359
    Prev
    Next
    INDEX
    Explanations

    names of institutions

    oai_token-act-pair · gemini-2.0-flash

    medical entities and institutions

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

    Hospitals and medical institutions

    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
    Negative Logits
    EDEFAULT
    -0.58
    AutoScale
    -0.56
    CloseOperation
    -0.54
     puberty
    -0.52
    ClientRect
    -0.52
     onPostExecute
    -0.52
     Piel
    -0.50
    RefreshLayout
    -0.49
    jelen
    -0.49
    AndEndTag
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.60
    /***/
    0.58
    numerusform
    0.57
    <?
    0.57
    ordinated
    0.57
    providedIn
    0.55
    webElement
    0.53
    usepackage
    0.50
    ,:),
    0.50
    Tē
    0.49
    Activations Density 0.511%

    No Known Activations