© 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. 3730
    Prev
    Next
    INDEX
    Explanations

    questions about what is being read and what will happen next

    oai_token-act-pair · gemini-2.0-flash

    next

    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
    HtmlAttribute
    -0.54
    AxisAlignment
    -0.49
    anera
    -0.46
    ropra
    -0.44
    piegel
    -0.43
    SequentialGroup
    -0.43
    fone
    -0.42
    typeorm
    -0.42
    早已
    -0.41
     initWithFrame
    -0.41
    POSITIVE LOGITS
     next
    3.61
    next
    3.27
    Next
    2.92
     Next
    2.86
     NEXT
    2.50
    NEXT
    2.41
     nächste
    2.09
     nächsten
    2.09
     nästa
    1.96
     næste
    1.95
    Activations Density 2.616%

    No Known Activations