© 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. 10689
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are required

    oai_token-act-pair · gemini-2.0-flash

    Mandatory

    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
     mandatory
    -0.72
    mandatory
    -0.70
     obligatory
    -0.69
    Mandatory
    -0.69
     Mandatory
    -0.67
     обяза
    -0.63
     compulsory
    -0.63
     obblig
    -0.61
     obrig
    -0.60
    oblig
    -0.60
    POSITIVE LOGITS
    __*/
    0.71
    fjspx
    0.71
     ویکی‌پدیای
    0.69
    SharedCtor
    0.68
    AndEndTag
    0.68
     newBuilder
    0.67
    tagHelperRunner
    0.66
    Rohy
    0.62
    شهاد
    0.62
     répondit
    0.62
    Activations Density 6.928%

    No Known Activations