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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10161
    Prev
    Next
    INDEX
    Explanations

    elements of a news article about the TV show X-Factor, especially when discussing judges and pay.

    oai_token-act-pair · gemini-2.0-flash

    judge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/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
    يكب
    -0.59
    BeginContext
    -0.56
    \{\\
    -0.51
    kháu
    -0.50
     NgModule
    -0.50
     váll
    -0.49
     ErrIntOverflow
    -0.49
    gway
    -0.49
     resultCode
    -0.48
    DeleteBehavior
    -0.48
    POSITIVE LOGITS
     judges
    1.44
     judging
    1.41
     judge
    1.31
    Judges
    1.27
     Judges
    1.27
     juges
    1.14
    judge
    1.13
    jud
    1.12
     judged
    1.11
     Judge
    1.09
    Activations Density 0.748%

    No Known Activations