© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8921
    Prev
    Next
    INDEX
    Explanations

    words related to installing or configuring software and rebooting and connecting

    oai_token-act-pair · gemini-2.0-flash

    boot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ierzch
    -0.55
    resave
    -0.52
     resourceCulture
    -0.50
    fjspx
    -0.50
    kháu
    -0.49
     trás
    -0.47
     virulence
    -0.47
    utnik
    -0.46
    CROSSTALK
    -0.46
    typeorm
    -0.45
    POSITIVE LOGITS
    WithMany
    0.62
    WireFormatLite
    0.57
    @[+][
    0.54
     IndexPath
    0.54
    ddots
    0.51
     JpaRepository
    0.51
    mappedBy
    0.51
    stateParams
    0.50
    #
    0.50
    openhague
    0.50
    Activations Density 0.735%

    No Known Activations