© 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. 13195
    Prev
    Next
    INDEX
    Explanations

    words commonly found in technical writing/documentation

    oai_token-act-pair · gemini-2.0-flash

    "or" in other languages

    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
    usermodel
    -0.72
    CodedInputStream
    -0.71
     mxArray
    -0.71
     Infórmanos
    -0.53
     pinulongan
    -0.52
     transfieras
    -0.52
    DockStyle
    -0.52
    SequentialGroup
    -0.52
    principalColumn
    -0.48
    principalTable
    -0.48
    POSITIVE LOGITS
     or
    3.86
     или
    2.69
    或
    2.47
     atau
    2.33
    或者
    2.25
     eller
    2.20
    หรือ
    2.17
     oder
    2.16
     nebo
    2.16
     یا
    2.13
    Activations Density 15.614%

    No Known Activations