© 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. 13721
    Prev
    Next
    INDEX
    Explanations

    names, initials, and other information in physics publications.

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    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
    ⓧ
    -0.76
    tagHelperRunner
    -0.75
     correctes
    -0.67
    MigrationBuilder
    -0.64
    #+#
    -0.63
     pinulongan
    -0.63
    localctx
    -0.63
     "..\..\..\
    -0.61
     Monfieur
    -0.61
    Kanpo
    -0.59
    POSITIVE LOGITS
    <bos>
    0.79
    Geografía
    0.49
    ↵↵
    0.44
    <eos>
    0.44
    SOUNDBITE
    0.41
    想
    0.41
    色
    0.41
     We
    0.40
     }^{[
    0.40
    ↵
    0.40
    Activations Density 1.737%

    No Known Activations