© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13628
    Prev
    Next
    INDEX
    Explanations

    text in political opinion pieces.

    oai_token-act-pair · gemini-2.0-flash

    political opinions

    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
    #+#
    -0.52
    ছ
    -0.44
    /*
    -0.42
     điểm
    -0.41
    URES
    -0.38
    HttpStatus
    -0.36
    спита
    -0.36
    kit
    -0.36
     spo
    -0.35
    体
    -0.35
    POSITIVE LOGITS
    
    0.95
     utafitiHapana
    0.81
     impeachment
    0.74
     impea
    0.74
     Мексичка
    0.73
    IntoConstraints
    0.69
    NameInMap
    0.68
    nities
    0.66
    qrstuvwxyz
    0.66
     Marxism
    0.64
    Activations Density 21.095%

    No Known Activations