© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11208
    Prev
    Next
    INDEX
    Explanations

    references to addresses, universities, and directions, particularly those related to the Rotterdam Metro

    oai_token-act-pair · gemini-2.0-flash

    Places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    #+#
    -0.79
    WebElementEntity
    -0.76
     typelib
    -0.76
    contentLoaded
    -0.71
    bootstrapcdn
    -0.68
     createState
    -0.67
    InitVars
    -0.66
    ={`/
    -0.65
    principalColumn
    -0.63
    AsUp
    -0.63
    POSITIVE LOGITS
    Rüyada
    0.54
     pitié
    0.35
    طيع
    0.35
     uwagi
    0.34
     Hotspur
    0.33
    Msp
    0.33
    AutoScaleMode
    0.33
     وتسجيلات
    0.33
     StyleSheet
    0.32
    gelopen
    0.32
    Activations Density 0.174%

    No Known Activations