© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12310
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to "working," particularly in the context of code, programs or other systems

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    föra
    -0.52
    riever
    -0.50
    </h6>
    -0.46
    Dere
    -0.45
     ITIS
    -0.45
    ंदर
    -0.44
    hich
    -0.43
    agerie
    -0.43
    젝
    -0.42
     proposal
    -0.42
    POSITIVE LOGITS
     defaultstate
    0.77
    ✨:
    0.71
    webElementGuid
    0.66
    цездатний
    0.66
     EconPapers
    0.66
    COUVER
    0.63
    XtraGrid
    0.63
    Билгалдахарш
    0.63
     inoxydable
    0.62
     tartalomajánló
    0.60
    Activations Density 1.080%

    No Known Activations