© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14119
    Prev
    Next
    INDEX
    Explanations

    strings in various coding languages, especially those enclosed in quotation marks and brackets.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    SequentialGroup
    -0.87
    tvguidetime
    -0.84
    sidemargin
    -0.67
    
    -0.67
     समीक्षाओं
    -0.62
     gyhoeddwyd
    -0.62
     relâche
    -0.61
    Personensuche
    -0.61
     المعيارى
    -0.61
     незавершена
    -0.60
    POSITIVE LOGITS
    仔
    0.47
     bunch
    0.46
    ris
    0.45
    bs
    0.45
     thân
    0.44
    GUILayout
    0.43
     etc
    0.43
    ử
    0.43
     thủ
    0.42
    ற்று
    0.42
    Activations Density 2.684%

    No Known Activations