© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11083
    Prev
    Next
    INDEX
    Explanations

    the word "that" and words surrounding it, possibly to identify relative clauses in sentences

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act · gemini-2.0-flash

    that

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     that
    -0.81
     المعيارى
    -0.54
    that
    -0.54
    TypedDataSet
    -0.53
     bahwa
    -0.52
     foglal
    -0.52
     THAT
    -0.51
    BufferException
    -0.50
     taxable
    -0.50
    epsfig
    -0.49
    POSITIVE LOGITS
    UserScript
    0.73
     AssemblyTitle
    0.71
     OnInit
    0.71
    ganu
    0.63
    providedIn
    0.60
     iArr
    0.60
    IMPORTED
    0.59
    StoryboardSegue
    0.58
    MockBean
    0.56
     posX
    0.55
    Activations Density 8.224%

    No Known Activations