© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5544
    Prev
    Next
    INDEX
    Explanations

    names and descriptions of trails

    oai_token-act-pair · gemini-2.0-flash

    decimals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     فريبيس
    -0.91
     betweenstory
    -0.89
    mergeFrom
    -0.83
    __':
    -0.75
     CreateTagHelper
    -0.66
     cherchés
    -0.64
    __':
    -0.62
    GOTREF
    -0.61
     pinulongan
    -0.60
     mû
    -0.60
    POSITIVE LOGITS
     .
    1.95
     (.
    1.59
    (.
    1.42
     half
    1.34
    -.
    1.33
     [.
    1.32
    /.
    1.29
    =.
    1.27
     $.
    1.18
     ½
    1.18
    Activations Density 4.459%

    No Known Activations