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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1685
    Prev
    Next
    INDEX
    Explanations

    customer reviews of professional services on the internet

    oai_token-act-pair · gemini-2.0-flash

    positive reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
    InitVars
    -0.64
    IndentedString
    -0.60
    Portale
    -0.59
     '\\;'
    -0.57
    ,‎
    -0.57
     nahilalakip
    -0.54
    GEBURTSDATUM
    -0.54
     colectivos
    -0.54
    -(
    -0.53
    izability
    -0.53
    POSITIVE LOGITS
    WebControls
    0.49
     cô
    0.49
    сво
    0.48
    Américaine
    0.47
     Someone
    0.47
     Some
    0.45
     They
    0.45
    atecas
    0.45
     That
    0.45
     This
    0.45
    Activations Density 6.789%

    No Known Activations