© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13497
    Prev
    Next
    INDEX
    Explanations

    file names, publisher mentions, and code diffs

    oai_token-act-pair · gemini-2.0-flash

    pdf

    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
    setVerticalGroup
    -0.56
    htë
    -0.52
    Tracce
    -0.49
    ruti
    -0.49
    xler
    -0.48
     LUMP
    -0.48
    ntable
    -0.48
     Ανακτήθηκε
    -0.47
    
    -0.46
    contentLoaded
    -0.46
    POSITIVE LOGITS
    __":
    0.45
     gita
    0.44
    ✨:
    0.43
    iduous
    0.42
    jsxFileName
    0.40
    **/
    0.40
    toMatchSnapshot
    0.40
    }))
    0.39
     bittersweet
    0.39
     santai
    0.38
    Activations Density 0.055%

    No Known Activations