© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 332
    Prev
    Next
    INDEX
    Explanations

    text related to legal proceedings and court decisions, especially around the rights of beneficiaries and employees.

    oai_token-act-pair · gemini-2.0-flash

    Legal and financial contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.61
     esternos
    -0.49
     confronti
    -0.48
    extAlignment
    -0.47
    ukone
    -0.45
    zeitige
    -0.45
     sfeer
    -0.42
    蚪
    -0.41
    gdala
    -0.40
    ämään
    -0.40
    POSITIVE LOGITS
    
    0.77
    rungsseite
    0.71
    mapStateToProps
    0.67
    sizeCache
    0.58
    WaitGroup
    0.58
     समीक्षाएं
    0.56
    ISupport
    0.56
    MethodManager
    0.56
    getMenuInflater
    0.56
    TypedDataSet
    0.55
    Activations Density 15.808%

    No Known Activations