© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2846
    Prev
    Next
    INDEX
    Explanations

    the phrase "one or more"

    oai_token-act-pair · gemini-2.0-flash

    more

    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
    ChildScrollView
    -0.88
    +#+#
    -0.64
     snippetHide
    -0.58
    mapStateToProps
    -0.56
    Hochspringen
    -0.56
    Референце
    -0.56
     ComVisible
    -0.55
    writerow
    -0.54
    Παραπομπές
    -0.54
    原始内容存档于
    -0.54
    POSITIVE LOGITS
    requireNonNull
    0.51
    واه
    0.48
    óa
    0.48
     odst
    0.46
    κτή
    0.46
    Слу
    0.45
     setType
    0.45
    richlet
    0.45
    luor
    0.45
     obstante
    0.45
    Activations Density 0.851%

    No Known Activations