© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12915
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and software licensing jargon

    oai_token-act-pair · gemini-2.0-flash

    code and licenses

    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
     a
    -0.66
     in
    -0.64
     as
    -0.63
     
    -0.62
     the
    -0.61
     put
    -0.60
     for
    -0.59
    ,
    -0.58
     The
    -0.57
     on
    -0.57
    POSITIVE LOGITS
    Rhestr
    1.23
    GraphicsUnit
    1.19
     تضيفلها
    1.16
    ValueStyle
    1.05
    sidemargin
    1.05
     EconPapers
    1.04
     AssemblyCulture
    1.04
     مشين
    1.03
     <=",
    1.03
    WebVitals
    1.02
    Activations Density 8.620%

    No Known Activations