© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6502
    Prev
    Next
    INDEX
    Explanations

    the word "seen" or words related to understanding or thoughts

    oai_token-act-pair · gemini-2.0-flash

    seen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     found
    -0.96
    ↵↵
    -0.77
    <bos>
    -0.76
    2
    -0.72
     seen
    -0.69
    ,
    -0.67
    .
    -0.66
    3
    -0.63
    -
    -0.63
    1
    -0.63
    POSITIVE LOGITS
     $_"
    1.34
     Jefus
    1.33
     iſt
    1.30
     itſelf
    1.27
    ſelves
    1.27
     Theſe
    1.22
     Efq
    1.22
     houſe
    1.21
     Eſ
    1.20
    ſelf
    1.16
    Activations Density 0.899%

    No Known Activations