© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13996
    Prev
    Next
    INDEX
    Explanations

    photo captions attributing images to Getty Images

    oai_token-act-pair · gemini-2.0-flash

    diverse photo credits and references

    np_token-act-pair-logits · gpt-4o-mini

    Famous people problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    +#+#
    -0.56
    Navigation
    -0.43
     signature
    -0.43
    DllImport
    -0.42
    obb
    -0.40
     summary
    -0.40
     tanı
    -0.40
    ḵ
    -0.39
    /-/
    -0.39
    with
    -0.38
    POSITIVE LOGITS
    NOPQRST
    0.88
     الحره
    0.74
    DrawerToggle
    0.64
     للاسماء
    0.64
     nahilalakip
    0.64
    endő
    0.57
    })`
    0.56
     विश्वसनीयता
    0.55
    المشاركات
    0.55
     }{@
    0.54
    Activations Density 1.731%

    No Known Activations