© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11820
    Prev
    Next
    INDEX
    Explanations

    text from internet forum posts

    oai_token-act-pair · gemini-2.0-flash

    internet/code text with special chars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Meksiku
    -0.83
    sizeCache
    -0.79
     GenerationType
    -0.66
    TypedDataSet
    -0.66
    awtextra
    -0.62
     оригіналу
    -0.59
     autorytatywna
    -0.57
    hdysval
    -0.56
     <>",
    -0.56
     kasarigan
    -0.55
    POSITIVE LOGITS
    tagext
    0.48
    çim
    0.48
    TagMode
    0.47
    裟
    0.47
     com
    0.47
     estekak
    0.47
    }}/>
    0.46
     تانيه
    0.46
    western
    0.45
    arama
    0.45
    Activations Density 1.324%

    No Known Activations