© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12286
    Prev
    Next
    INDEX
    Explanations

    discourse markers such as "things that", "that", "like", "suggest", "I", "you", "do"

    oai_token-act-pair · gemini-2.0-flash

    thing/things

    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
     B
    -0.54
     P
    -0.52
     
    -0.50
     V
    -0.46
     son
    -0.46
    </strong>
    -0.46
     N
    -0.44
     b
    -0.44
    5
    -0.43
     p
    -0.42
    POSITIVE LOGITS
    ValueStyle
    1.13
     Signalez
    1.00
     itſelf
    0.99
     myſelf
    0.93
     Италијани
    0.85
    Personensuche
    0.85
     nonUne
    0.85
     becauſe
    0.85
     uſed
    0.84
    rawDesc
    0.83
    Activations Density 14.782%

    No Known Activations