© 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. 3805
    Prev
    Next
    INDEX
    Explanations

    angle-bracket-enclosed parameters and object attributes with names that include the words "width", "size", "channel", "& number."

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     v
    -0.93
     V
    -0.92
     I
    -0.91
     M
    -0.90
     J
    -0.85
     van
    -0.84
     et
    -0.84
     T
    -0.84
     l
    -0.83
     D
    -0.83
    POSITIVE LOGITS
     itſelf
    1.48
    ſelf
    1.29
     pleaſure
    1.27
     myſelf
    1.27
     Anſ
    1.27
    ſelves
    1.20
     ſche
    1.18
     Majefty
    1.18
     auffi
    1.18
     themſelves
    1.18
    Activations Density 9.985%

    No Known Activations