© 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. 11320
    Prev
    Next
    INDEX
    Explanations

    angles in scientific notation (e.g. 45^\circ)

    oai_token-act-pair · gemini-2.0-flash

    Math mode formatting

    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
    اند
    -0.55
     range
    -0.52
    ACEAE
    -0.51
    Atoi
    -0.50
     голос
    -0.48
    uvres
    -0.48
    vcut
    -0.48
    мені
    -0.48
    straining
    -0.47
     lijn
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.87
     JpaRepository
    0.68
     bezeichneter
    0.63
    ----</
    0.63
     فريبيس
    0.62
     otomatig
    0.62
    ThroughAttribute
    0.60
    InjectAttribute
    0.59
     disambiguazione
    0.57
    StoryboardSegue
    0.57
    Activations Density 0.397%

    No Known Activations