© 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. 13493
    Prev
    Next
    INDEX
    Explanations

    snippets of code with the words "fields", "ids", "state", "args", "GET", or "Param"

    oai_token-act-pair · gemini-2.0-flash

    close parenthesis

    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
     CreateTagHelper
    -0.81
    schild
    -0.63
     Abonnez
    -0.61
    oredCriteria
    -0.60
     كومونز
    -0.60
     Audiodateien
    -0.59
     مشين
    -0.59
    WireFormatLite
    -0.59
    AsUp
    -0.59
    AntiForgeryToken
    -0.58
    POSITIVE LOGITS
    StructEnd
    0.60
    SBATCH
    0.56
    fortawesome
    0.50
     للاسماء
    0.47
    )))
    0.47
    )))));
    0.46
    ')}}"
    0.45
    ↵
    0.44
    UserController
    0.44
     ratios
    0.42
    Activations Density 1.510%

    No Known Activations