© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11934
    Prev
    Next
    INDEX
    Explanations

    the word "see" in an article, often in the context of something visual or apparent

    oai_token-act-pair · gemini-2.0-flash

    see

    np_max-act · gemini-2.0-flash

    see

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    LookAnd
    -0.91
    BufferException
    -0.79
    DockStyle
    -0.75
    #+#
    -0.75
     <>",
    -0.71
     QtWidgets
    -0.69
    enderror
    -0.68
     mergeFrom
    -0.68
    HomeAsUpEnabled
    -0.67
     propOrder
    -0.66
    POSITIVE LOGITS
     boto
    0.60
     <<<<<<<<<<<<<<
    0.56
    Референце
    0.55
    caches
    0.54
    ENZA
    0.52
    ływ
    0.52
    Cabe
    0.50
    苷
    0.47
     merce
    0.47
     piele
    0.47
    Activations Density 0.377%

    No Known Activations