© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11793
    Prev
    Next
    INDEX
    Explanations

    HTML image tags and the word 'temp' in code

    oai_token-act-pair · gemini-2.0-flash

    files/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     betweenstory
    -0.84
    <eos>
    -0.64
    ↵↵
    -0.62
    canestro
    -0.60
    #+#
    -0.55
    oaks
    -0.54
    WaitGroup
    -0.51
     ddelweddau
    -0.51
    AntiForgeryToken
    -0.51
    +#+
    -0.50
    POSITIVE LOGITS
     purpoſe
    0.81
     Anſ
    0.81
     ſhe
    0.81
     whoſe
    0.78
     ModelExpression
    0.77
     quæ
    0.76
     becauſe
    0.74
     Houſe
    0.73
     leaſt
    0.73
     houſe
    0.71
    Activations Density 1.300%

    No Known Activations