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. 2322
    Prev
    Next
    INDEX
    Explanations

    descriptive language about dance or house music

    oai_token-act-pair · gemini-2.0-flash

    Music, battles, and fighting

    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
     ligiloj
    -0.79
    ArgsConstructor
    -0.76
    onAttach
    -0.74
     autorytatywna
    -0.71
    bootstrapcdn
    -0.66
    WebVitals
    -0.66
    Datuak
    -0.66
    Tikang
    -0.65
     endwhile
    -0.65
    InitVars
    -0.63
    POSITIVE LOGITS
    
    0.48
    พัก
    0.47
    pragma
    0.46
     ASE
    0.46
     Fantas
    0.44
     didac
    0.43
     ingrat
    0.42
     kidding
    0.42
     IDisposable
    0.41
     Hydra
    0.40
    Activations Density 1.136%

    No Known Activations