© 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. 6300
    Prev
    Next
    INDEX
    Explanations

    section-like breaks in text, such as parentheses, semicolons, bullets, and section headers

    oai_token-act-pair · gemini-2.0-flash

    each

    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
     Bioaccumulative
    -0.65
     שוליים
    -0.60
    EDEFAULT
    -0.59
    AnchorStyles
    -0.57
    findpost
    -0.54
    TagMode
    -0.54
     ModelExpression
    -0.53
     CURLOPT
    -0.53
     otomatig
    -0.52
     كومونز
    -0.51
    POSITIVE LOGITS
     each
    3.00
    each
    2.48
     Each
    2.39
    Each
    2.38
     EACH
    2.13
    EACH
    1.95
     chacun
    1.77
     chacune
    1.72
     masing
    1.69
     mỗi
    1.65
    Activations Density 3.115%

    No Known Activations