© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9161
    Prev
    Next
    INDEX
    Explanations

    uses positive language about facts/research

    oai_token-act-pair · gemini-2.0-flash

    descriptive phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     שוליים
    -0.48
    semver
    -0.46
    ̉
    -0.46
    Referensi
    -0.45
    ho
    -0.43
     Krakowie
    -0.43
     Diman
    -0.43
    וּ
    -0.42
    um
    -0.42
    Ho
    -0.42
    POSITIVE LOGITS
     hie
    0.79
     hl
    0.79
     hit
    0.78
     h
    0.78
     hi
    0.77
     архивлан
    0.74
     hii
    0.68
     Hi
    0.67
    goku
    0.67
     bin
    0.66
    Activations Density 3.112%

    No Known Activations