© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12035
    Prev
    Next
    INDEX
    Explanations

    code snippets and html tags

    oai_token-act-pair · gemini-2.0-flash

    uncommon words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    setVerticalGroup
    -0.67
    expandindo
    -0.59
    dden
    -0.57
     Kader
    -0.52
     eye
    -0.52
    ogly
    -0.51
     Promoting
    -0.51
    EndInit
    -0.50
    ioutil
    -0.50
    ynb
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.60
     betweenstory
    0.59
     nakalista
    0.58
     surla
    0.56
     aureus
    0.52
     getItemId
    0.51
    adpleegd
    0.50
     egna
    0.49
    maketitle
    0.49
     gruppe
    0.48
    Activations Density 0.047%

    No Known Activations