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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2309
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    oai_token-act-pair · gemini-2.0-flash

    HTML tags

    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
    </b>
    -1.45
    </strong>
    -1.31
    </h4>
    -1.03
    </h1>
    -0.98
    </u>
    -0.95
    </blockquote>
    -0.93
    </h5>
    -0.89
    </i>
    -0.87
    </h3>
    -0.82
    </s>
    -0.75
    POSITIVE LOGITS
     ComVisible
    0.68
    ✨:
    0.65
    SharedDtor
    0.59
     smtplib
    0.59
     يتيمه
    0.57
    vode
    0.57
    ImageContext
    0.57
    ValueStyle
    0.56
     TextAppearance
    0.56
     photolibrary
    0.56
    Activations Density 6.522%

    No Known Activations