© 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
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 10866
    Prev
    Next
    INDEX
    Explanations

    the letters "Sar"

    oai_token-act-pair · gemini-2.0-flash

    Sar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    contentLoaded
    -0.48
    MethodManager
    -0.48
     beginnetje
    -0.48
     actionTypes
    -0.48
    Życiorys
    -0.47
     møte
    -0.47
    تماد
    -0.45
    routeProvider
    -0.45
     IRL
    -0.44
    føring
    -0.44
    POSITIVE LOGITS
     picha
    0.56
    \{\\
    0.55
     paff
    0.53
     estekak
    0.51
     JAXBElement
    0.51
    Distribuzione
    0.50
    Jegyzetek
    0.49
     inappropriés
    0.49
    Phas
    0.49
     مرئيه
    0.48
    Activations Density 1.215%

    No Known Activations