© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10776
    Prev
    Next
    INDEX
    Explanations

    HTML and code snippets, including tags and potentially some Portuguese words

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AccessorTable
    -0.70
    WebElementEntity
    -0.64
    igshid
    -0.64
    Jereo
    -0.63
    ImageContext
    -0.59
    Portail
    -0.55
    WriteBarrier
    -0.54
    piegel
    -0.54
    ListItemIcon
    -0.53
     HasFactory
    -0.53
    POSITIVE LOGITS
     Volga
    0.57
     GENERATED
    0.56
     متعلقه
    0.55
    MCA
    0.54
    gonic
    0.53
     Kins
    0.53
    Cambios
    0.51
     astore
    0.51
    trons
    0.50
    ]--;
    0.50
    Activations Density 0.521%

    No Known Activations