© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4858
    Prev
    Next
    INDEX
    Explanations

    research paper titles and figure references

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WithIOException
    -0.58
     picioare
    -0.53
     răm
    -0.51
     kampen
    -0.50
     vecka
    -0.50
    jähriger
    -0.49
     scattata
    -0.49
     '\\;'
    -0.47
     skolan
    -0.47
     dovuto
    -0.47
    POSITIVE LOGITS
     presence
    0.69
     total
    0.66
     absence
    0.66
     present
    0.64
     AttributeSet
    0.62
    ℏ
    0.57
     amount
    0.57
     existence
    0.55
    WebControls
    0.55
    /−
    0.55
    Activations Density 3.430%

    No Known Activations