© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13938
    Prev
    Next
    INDEX
    Explanations

    phrases indicating estimation or approximation

    oai_token-act-pair · gemini-2.0-flash

    Give or take

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    latego
    -0.52
    ChildScrollView
    -0.46
    ivamente
    -0.44
    otriz
    -0.44
     MainAxisSize
    -0.44
    sequently
    -0.43
     없습니다
    -0.42
    ;">
    -0.40
    AndEndTag
    -0.40
    fromCharCode
    -0.39
    POSITIVE LOGITS
    Datuak
    0.80
     ModelExpression
    0.77
     CreateTagHelper
    0.71
    buss
    0.67
    TestingModule
    0.66
    jspx
    0.64
    tagHelperRunner
    0.60
    şiv
    0.60
    ttle
    0.59
    cyd
    0.59
    Activations Density 3.736%

    No Known Activations