© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7375
    Prev
    Next
    INDEX
    Explanations

    words relating to phones, computers, web browsing, or other electronic devices

    oai_token-act-pair · gemini-2.0-flash

    mobile devices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     redé
    -0.62
     Efq
    -0.58
    DMETHOD
    -0.55
     leaſt
    -0.53
     cell
    -0.53
     تانيه
    -0.51
     bhi
    -0.50
     ostavi
    -0.50
     yf
    -0.50
    OMO
    -0.50
    POSITIVE LOGITS
    RuleContext
    0.51
    onsored
    0.50
    fjspx
    0.50
    éről
    0.50
     betweenstory
    0.49
     externi
    0.49
     saltar
    0.48
    govine
    0.48
    VIAF
    0.48
    🥞
    0.46
    Activations Density 2.272%

    No Known Activations