© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14128
    Prev
    Next
    INDEX
    Explanations

    blog-style posts with long breaks/indents between paragraphs

    oai_token-act-pair · gemini-2.0-flash

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -1.05
     Mellon
    -0.53
    multirow
    -0.50
    Geplaatst
    -0.50
     شم
    -0.49
     draw
    -0.46
    thon
    -0.46
     Bureau
    -0.46
    ály
    -0.46
    ň
    -0.45
    POSITIVE LOGITS
    addPreferredGap
    0.58
    VersionUID
    0.58
     becauſe
    0.54
     surla
    0.46
    UnknownFields
    0.46
    OrBuilder
    0.46
     Theſe
    0.46
     ſeveral
    0.45
    reportWebVitals
    0.45
    ^(@)
    0.45
    Activations Density 0.130%

    No Known Activations