© 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. 11948
    Prev
    Next
    INDEX
    Explanations

    speech and associated conversational context in political reporting.

    oai_token-act-pair · gemini-2.0-flash

    reporting something

    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
     صوتيه
    -0.68
     himo
    -0.66
     Infórmanos
    -0.63
    MeasureSpec
    -0.62
    ControllerAdvice
    -0.61
     '\\;'
    -0.60
    Datuak
    -0.59
     createSlice
    -0.58
    قایناق‌لار
    -0.58
    الإنجليزية
    -0.57
    POSITIVE LOGITS
    astéroïdes
    0.57
    ItemSelected
    0.53
     Veil
    0.50
     HttpNotFound
    0.49
    jsonp
    0.47
    AnimationsModule
    0.46
    ulmuş
    0.46
     yesterday
    0.45
    TableAdapter
    0.45
     ieri
    0.45
    Activations Density 3.071%

    No Known Activations