© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7171
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations found in technical documentation, especially code and legal documents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     DT
    -0.76
     DCA
    -0.68
    DP
    -0.67
     Dara
    -0.66
    DF
    -0.64
     DPR
    -0.64
     DSA
    -0.64
     DP
    -0.63
     Diſ
    -0.63
     DHS
    -0.62
    POSITIVE LOGITS
    قایناق‌لار
    0.59
     ResponseEntity
    0.59
    popo
    0.59
    +#+#
    0.58
    SequentialGroup
    0.57
     PicClick
    0.56
    atisfaction
    0.56
     Италијани
    0.55
     >=",
    0.55
    beforeEach
    0.55
    Activations Density 1.793%

    No Known Activations