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. 1648
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measurement

    oai_token-act-pair · gemini-2.0-flash

    0

    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
    ethe
    -0.57
     nakalista
    -0.55
     виправивши
    -0.53
     bodyParser
    -0.52
    AndEndTag
    -0.51
    .”)
    -0.51
     Biele
    -0.50
    XmlAccessorType
    -0.50
    }());
    -0.50
    ="./
    -0.50
    POSITIVE LOGITS
     برانيه
    0.59
    ็จ
    0.52
    TemporalType
    0.52
    liosis
    0.49
    Wpf
    0.47
    wpi
    0.45
    ribusi
    0.45
     facie
    0.44
     nahilalakip
    0.44
    SCAPE
    0.43
    Activations Density 6.070%

    No Known Activations