© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12747
    Prev
    Next
    INDEX
    Explanations

    words used in product descriptions

    oai_token-act-pair · gemini-2.0-flash

    terms related to mapping and data structures

    np_token-act-pair-logits · gpt-4o-mini

    equipment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Bindings
    -0.54
    requireNonNull
    -0.50
     AssertionError
    -0.50
     ditentukan
    -0.48
    andExpect
    -0.47
     inconvénients
    -0.47
    ElementException
    -0.46
    espère
    -0.46
     conséquences
    -0.46
     العالمي
    -0.45
    POSITIVE LOGITS
     ddelweddau
    0.67
     offices
    0.60
    NameInMap
    0.58
     ModelExpression
    0.57
     AssemblyCulture
    0.56
     autorytatywna
    0.55
    Бахар
    0.55
    __":
    0.55
     mergeFrom
    0.55
    цездатний
    0.55
    Activations Density 4.114%

    No Known Activations