© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11054
    Prev
    Next
    INDEX
    Explanations

    examples and scenarios, often in the form of a request for help

    oai_token-act-pair · gemini-2.0-flash

    giving examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Вариан
    -0.67
    Alternative
    -0.66
    alternative
    -0.66
     Alternative
    -0.66
     alternatives
    -0.64
     Options
    -0.63
     alternative
    -0.62
    efeller
    -0.62
     Varieties
    -0.61
     Choices
    -0.60
    POSITIVE LOGITS
    addContainerGap
    0.64
    ostante
    0.51
    putExtra
    0.51
    <bos>
    0.50
     चीज़ों
    0.48
    SetBool
    0.46
    Uninitialized
    0.45
     chi̍t
    0.45
    InitStruct
    0.45
    הערות
    0.45
    Activations Density 1.028%

    No Known Activations