© 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. 11250
    Prev
    Next
    INDEX
    Explanations

    words used to describe the architecture and layout of church buildings

    oai_token-act-pair · gemini-2.0-flash

    tower

    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
    InsertCommand
    -0.58
    =").
    -0.54
    pośred
    -0.54
    }`}>
    -0.53
    */)
    -0.52
     dignité
    -0.52
    esez
    -0.51
    }(),
    -0.51
    }{*}{
    -0.51
     HONORABLE
    -0.51
    POSITIVE LOGITS
    elemField
    0.53
    ніципалі
    0.51
    principalColumn
    0.50
     nahilalakip
    0.50
    FormTagHelper
    0.49
    AccessorTable
    0.46
    pinos
    0.45
    KURZBESCHREIBUNG
    0.45
    чим
    0.44
    oa̍t
    0.44
    Activations Density 1.614%

    No Known Activations