© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    positive or negative judgements in sports news

    oai_token-act-pair · gemini-2.0-flash

    Negative or strong emotions

    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
    AddHtmlAttribute
    -0.75
    ModelBuilder
    -0.54
    ByVersion
    -0.54
     PTT
    -0.51
     незавершена
    -0.51
    ApiModel
    -0.48
    feof
    -0.48
     geográfica
    -0.48
     Tratt
    -0.47
    addGroup
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.68
     дописавши
    0.66
     autorytatywna
    0.62
    tinyos
    0.61
    
    0.53
    tagHelperRunner
    0.52
     nahilalakip
    0.52
    expandindo
    0.52
    })();
    0.52
    endphp
    0.49
    Activations Density 6.774%

    No Known Activations