© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14422
    Prev
    Next
    INDEX
    Explanations

    code or hexadecimal representations

    oai_token-act-pair · gemini-2.0-flash

    hexadecimal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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>
    -0.87
     resourceCulture
    -0.84
     Савезне
    -0.80
    Билгалдахарш
    -0.69
     محفوظة
    -0.68
    ьаж
    -0.67
     bezeichneter
    -0.67
     <>",
    -0.65
     otomatig
    -0.64
     ostavi
    -0.64
    POSITIVE LOGITS
    דים
    0.49
     Lotion
    0.48
     يتيمه
    0.48
    rxjs
    0.47
    tesse
    0.47
     Hoops
    0.46
    ビリ
    0.45
     Haze
    0.45
    ι
    0.44
     Sludge
    0.44
    Activations Density 31.566%

    No Known Activations