© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6409
    Prev
    Next
    INDEX
    Explanations

    words related to providing documents

    oai_token-act-pair · gemini-2.0-flash

    copy, a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     copy
    -2.11
     Copy
    -1.92
    copy
    -1.91
    Copy
    -1.84
     copies
    -1.73
     COPY
    -1.68
     Copies
    -1.61
     copying
    -1.59
     copie
    -1.52
    COPY
    -1.48
    POSITIVE LOGITS
    rungsseite
    0.54
    parsedMessage
    0.54
     AssemblyCompany
    0.54
     disambiguazione
    0.53
    Бахар
    0.53
    JoinColumn
    0.52
     JsonConvert
    0.51
     InputDecoration
    0.51
    MENAFN
    0.51
    webElementGuid
    0.50
    Activations Density 2.425%

    No Known Activations