© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11777
    Prev
    Next
    INDEX
    Explanations

    legal code references

    oai_token-act-pair · gemini-2.0-flash

    Legal, news snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     NYS
    -0.87
    NYC
    -0.81
     NYC
    -0.81
     NY
    -0.79
     NYPD
    -0.77
    NY
    -0.73
     SUNY
    -0.73
     Schenectady
    -0.71
     Brooklyn
    -0.69
     Bronx
    -0.68
    POSITIVE LOGITS
     defaultstate
    1.09
    ">//
    0.61
    TintMode
    0.61
     jScrollPane
    0.60
    PyExc
    0.58
    Controllo
    0.58
    NewUrlParser
    0.56
     muualla
    0.56
    FilterChain
    0.55
     surla
    0.54
    Activations Density 0.939%

    No Known Activations