© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9886
    Prev
    Next
    INDEX
    Explanations

    text describing a company's image policy, especially regarding accurately representing items for sale

    oai_token-act-pair · gemini-2.0-flash

    differences

    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
     виправивши
    -0.56
    NewReader
    -0.54
    ReusableCell
    -0.53
    Grá
    -0.51
    urn
    -0.51
    oneof
    -0.51
    andExpect
    -0.50
    setDo
    -0.50
     }{@
    -0.49
    toThrow
    -0.49
    POSITIVE LOGITS
    SpringBootTest
    0.55
    Redacción
    0.51
    OGND
    0.50
    Bonjour
    0.48
    Remaining
    0.47
     Privacidade
    0.47
    はじめに
    0.47
    üyada
    0.46
    Források
    0.45
     transfieras
    0.45
    Activations Density 0.207%

    No Known Activations