© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5882
    Prev
    Next
    INDEX
    Explanations

    terms related to someone performing or acting a role, as well as superlatives like best and high

    oai_token-act-pair · gemini-2.0-flash

    achievements/highlights

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    webElement
    -0.65
    >(&
    -0.57
    FieldOffset
    -0.54
    DETAILED
    -0.53
    νον
    -0.52
    locke
    -0.51
    lotz
    -0.50
    ftagPool
    -0.50
    tät
    -0.49
    })->
    -0.49
    POSITIVE LOGITS
    انيف
    0.65
    ViewImports
    0.62
     typelib
    0.58
     mAdapter
    0.57
    onalds
    0.56
    tvguidetime
    0.54
     Signalez
    0.54
    曖昧さ回避
    0.54
    /******/
    0.52
    LLocation
    0.52
    Activations Density 1.959%

    No Known Activations