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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6911
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are comparative, superlative, or otherwise indicate a degree or quantity

    oai_token-act-pair · gemini-2.0-flash

    comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     betweenstory
    -0.62
     تانيه
    -0.55
    //
    -0.54
    extAlignment
    -0.53
     cherchés
    -0.52
     laten
    -0.52
    styleUrls
    -0.51
     lower
    -0.51
    __':
    
    -0.51
     Roskov
    -0.50
    POSITIVE LOGITS
    featureID
    0.57
    StreetMap
    0.54
    <bos>
    0.50
    woff
    0.49
    üch
    0.49
     HasFactory
    0.48
    tecla
    0.46
    verifyException
    0.45
     according
    0.45
     kaynağından
    0.45
    Activations Density 2.064%

    No Known Activations