© 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. 11717
    Prev
    Next
    INDEX
    Explanations

    the location of something, like "top of the page," and information about copyright and legal notices

    oai_token-act-pair · gemini-2.0-flash

    top

    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
     autorytatywna
    -0.61
     MainAxisSize
    -0.59
    <bos>
    -0.54
    henswürdigkeiten
    -0.50
     transférez
    -0.50
    mere
    -0.49
    անգ
    -0.48
    octanol
    -0.47
     Primero
    -0.47
    sendRedirect
    -0.47
    POSITIVE LOGITS
    InSection
    0.59
    topt
    0.58
    شهاد
    0.54
    Buffers
    0.54
     odkazy
    0.51
    LLocation
    0.50
    γε
    0.50
    ällor
    0.49
    èdia
    0.48
     समीक्षाओं
    0.47
    Activations Density 1.545%

    No Known Activations