© 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. 11459
    Prev
    Next
    INDEX
    Explanations

    the inventors and inventions

    oai_token-act-pair · gemini-2.0-flash

    frequently

    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
    DockStyle
    -0.67
    afficheront
    -0.60
    AutoScaleMode
    -0.57
    клопе
    -0.52
     FetchType
    -0.51
    ]--;
    -0.50
    WireFormatLite
    -0.49
    MemoryWarning
    -0.49
    loroethane
    -0.48
     <<<<<<<<<<<<<<
    -0.46
    POSITIVE LOGITS
     often
    2.41
     sometimes
    2.31
     Often
    2.08
    Often
    1.99
    often
    1.99
    sometimes
    1.99
     Sometimes
    1.90
     souvent
    1.80
     parfois
    1.78
     spesso
    1.77
    Activations Density 5.558%

    No Known Activations