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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14899
    Prev
    Next
    INDEX
    Explanations

    words including or starting with "Ja" or "Je" and possibly followed by other letters/hyphens.

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ⓧ
    -0.63
    Coroutine
    -0.57
     لينك
    -0.57
    dotenv
    -0.52
    BeginContext
    -0.51
     okuyayım
    -0.49
    lieved
    -0.49
    وصل
    -0.49
     InputDecoration
    -0.49
    migrationBuilder
    -0.48
    POSITIVE LOGITS
     الحره
    0.70
    )";
    
    0.61
    ']>
    0.59
     Administrativna
    0.50
     {}));
    0.50
     arşivlendi
    0.49
    RepeatedField
    0.48
    ItemBackground
    0.48
    ']);
    
    0.48
    "]);
    
    0.48
    Activations Density 1.123%

    No Known Activations