© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11960
    Prev
    Next
    INDEX
    Explanations

    strings of numbers, sometimes followed by letters, often within parentheses or brackets

    oai_token-act-pair · gemini-2.0-flash

    scientific publications & code

    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
    <bos>
    -0.79
    saraba
    -0.49
    bule
    -0.45
    MathML
    -0.45
    ibase
    -0.43
    ijų
    -0.42
    zas
    -0.42
    endu
    -0.41
    Referanser
    -0.41
    war
    -0.41
    POSITIVE LOGITS
     leaſt
    0.51
    Πηγή
    0.49
     purpoſe
    0.48
    InitVars
    0.44
     ſeveral
    0.42
     pleaſure
    0.42
     ſmall
    0.41
     whoſe
    0.41
     Wikimedijinoj
    0.41
     Efq
    0.41
    Activations Density 0.724%

    No Known Activations