© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8586
    Prev
    Next
    INDEX
    Explanations

    ambiguous, but seems to be looking for time, possession and self-reference.

    oai_token-act-pair · gemini-2.0-flash

    first/second person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ArgsConstructor
    -0.54
    addTab
    -0.50
    ItemGroup
    -0.49
     Unsplash
    -0.48
    Too
    -0.47
     crossword
    -0.47
    MethodManager
    -0.47
     AirPods
    -0.46
    πι
    -0.46
    hão
    -0.46
    POSITIVE LOGITS
    ChildScrollView
    0.78
     nahilalakip
    0.66
     Infórmanos
    0.66
    ctory
    0.66
    tersebut
    0.64
    SOUNDBITE
    0.62
    isissez
    0.60
    },[])
    0.59
    galus
    0.59
    GEBURTS
    0.59
    Activations Density 0.833%

    No Known Activations