© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3302
    Prev
    Next
    INDEX
    Explanations

    cooking instructions

    oai_token-act-pair · gemini-2.0-flash

    cooking directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     missed
    -0.54
     wasted
    -0.49
    出版年
    -0.48
     slowly
    -0.46
    uis
    -0.43
     hers
    -0.43
     miss
    -0.43
     potrzeb
    -0.42
    lji
    -0.42
    missed
    -0.42
    POSITIVE LOGITS
     '\\;'
    0.85
     BoxFit
    0.80
    MethodManager
    0.71
     ModelRenderer
    0.60
    hlungen
    0.59
    czema
    0.59
    جاج
    0.59
    EDEFAULT
    0.59
    homonymie
    0.58
    UnusedPrivate
    0.58
    Activations Density 7.440%

    No Known Activations