© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10784
    Prev
    Next
    INDEX
    Explanations

    common and generic phrases that don't have much informational content, and also phrases about planning or having experiences

    oai_token-act-pair · gemini-2.0-flash

    on

    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
     незавершена
    -1.15
     betweenstory
    -0.94
    StoryboardSegue
    -0.81
     Мексичка
    -0.76
    verwijspagina
    -0.76
    AndEndTag
    -0.73
     الرياضيه
    -0.72
     насељу
    -0.69
    ContentAsync
    -0.68
    StructEnd
    -0.68
    POSITIVE LOGITS
     on
    2.22
     On
    1.30
     auf
    1.21
    On
    1.16
     على
    1.13
     на
    1.12
     ON
    1.10
    on
    1.01
     på
    1.01
    onthe
    1.00
    Activations Density 1.861%

    No Known Activations