© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4647
    Prev
    Next
    INDEX
    Explanations

    contexts where a concept is questioned or challenged

    oai_token-act-pair · gemini-2.0-flash

    research/technical writing

    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
     worth
    -1.33
    worth
    -1.14
     WORTH
    -1.10
    Worth
    -1.06
     Worth
    -1.03
    WORTH
    -0.91
     worthwhile
    -0.73
     wort
    -0.58
     worthy
    -0.58
     value
    -0.58
    POSITIVE LOGITS
     Italijanski
    0.73
     jLabel
    0.73
    UserScript
    0.72
    ArrowToggle
    0.71
    cipar
    0.69
    getDescriptor
    0.67
    ритори
    0.66
     المعيارى
    0.65
    kloped
    0.65
    providedIn
    0.64
    Activations Density 1.399%

    No Known Activations