© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6959
    Prev
    Next
    INDEX
    Explanations

    references to technologies and systems

    oai_token-act-pair · gemini-2.0-flash

    abstract topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ConstraintMaker
    -1.09
     this
    -0.75
    MLLoader
    -0.74
     StatefulWidget
    -0.73
     it
    -0.73
    
    -0.72
     оно
    -0.72
     questa
    -0.69
    Portale
    -0.69
     это
    -0.68
    POSITIVE LOGITS
     you
    0.58
    Distribuzione
    0.53
    st
    0.47
    fein
    0.46
    ">—
    0.46
    のではないでしょうか
    0.44
    서
    0.42
    amey
    0.41
     we
    0.40
    Marshaller
    0.40
    Activations Density 3.609%

    No Known Activations