© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15131
    Prev
    Next
    INDEX
    Explanations

    code and structured text

    oai_token-act-pair · gemini-2.0-flash

    Code and website snippets

    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
    Autoritní
    -0.92
     autorytatywna
    -0.92
    WithIOException
    -0.68
     myſelf
    -0.66
    __":
    -0.64
     beſt
    -0.63
    utilisons
    -0.62
     ſtate
    -0.62
     betweenstory
    -0.61
     дописавши
    -0.60
    POSITIVE LOGITS
     vinto
    0.51
    matchers
    0.49
     nạn
    0.47
    Portály
    0.47
    <eos>
    0.47
    angliski
    0.47
     from
    0.46
    </strong>
    0.44
    ارية
    0.44
    انيف
    0.43
    Activations Density 4.637%

    No Known Activations