Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11168
    Prev
    Next
    INDEX
    Explanations

    references to application development

    oai_token-act-pair · gemini-2.0-flash

    programming terminology and syntax

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

    code and licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.47
    íso
    -0.44
     boo
    -0.44
    ().__
    -0.44
     Drapeau
    -0.44
     חיצוניים
    -0.44
     kaynağından
    -0.43
     ivelany
    -0.43
     ioutil
    -0.42
     estimés
    -0.42
    POSITIVE LOGITS
    writeFieldEnd
    0.84
     createSlice
    0.75
     BoxFit
    0.71
     FormBuilder
    0.66
     referenties
    0.62
     ++)
    0.59
     noqa
    0.59
     ErrIntOverflow
    0.58
     június
    0.54
    vacy
    0.54
    Activations Density 1.267%

    No Known Activations