© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9346
    Prev
    Next
    INDEX
    Explanations

    words related to interior design and architecture, especially related to minimalist design

    oai_token-act-pair · gemini-2.0-flash

    design and crafting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RenderAtEndOf
    -0.60
    idopsis
    -0.58
    WebElementEntity
    -0.56
    RegressionTest
    -0.56
     jsPsych
    -0.56
    fjspx
    -0.56
    keyColumn
    -0.56
    tocks
    -0.55
     noDo
    -0.54
     ElementRef
    -0.54
    POSITIVE LOGITS
    //
    0.47
    󠁢
    0.47
    føring
    0.46
     "..\..\
    0.43
     maxn
    0.42
     disappointed
    0.42
     sute
    0.40
     licencia
    0.40
    horabuena
    0.40
     Penh
    0.40
    Activations Density 4.229%

    No Known Activations