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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4603
    Prev
    Next
    INDEX
    Explanations

    conjunctions and relative pronouns and some spanish words

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    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
     \
    -0.92
    TableAdapter
    -0.65
    ♥♥
    -0.57
    nible
    -0.54
    ofus
    -0.51
    oltre
    -0.50
     Перейти
    -0.49
     ı
    -0.49
     nôtre
    -0.49
    "
    -0.48
    POSITIVE LOGITS
     himo
    0.69
    artifactId
    0.64
     ویکی‌پدیا
    0.63
    ';
    0.63
    ";
    0.59
    Viitteet
    0.58
    MigrationBuilder
    0.58
    __":
    
    0.58
    endcsname
    0.57
    ';
    
    0.56
    Activations Density 2.293%

    No Known Activations