© 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. 11598
    Prev
    Next
    INDEX
    Explanations

    a variety of formatting conventions, like bolding, bullets, asterisks, and special characters, along with some words denoting location

    oai_token-act-pair · gemini-2.0-flash

    Asterisks

    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
     tombe
    -0.47
    Rhestr
    -0.47
    uncias
    -0.46
    ulipas
    -0.41
     спра
    -0.41
    blico
    -0.40
    siella
    -0.40
     mayor
    -0.40
    usermodel
    -0.39
     PNP
    -0.39
    POSITIVE LOGITS
    AsUp
    0.65
     jScrollPane
    0.63
    SharedDtor
    0.63
    principalTable
    0.62
     Signalez
    0.60
     createSlice
    0.59
     EconPapers
    0.59
    textAppearance
    0.59
    }))
    0.58
    hoeddwyd
    0.57
    Activations Density 2.380%

    No Known Activations