© 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. 14983
    Prev
    Next
    INDEX
    Explanations

    the string "![" possibly related to images in a document

    oai_token-act-pair · gemini-2.0-flash

    ](

    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
    وص
    -0.44
     lengan
    -0.41
    いう
    -0.40
    AfterEach
    -0.40
    inous
    -0.40
    oting
    -0.40
    DOI
    -0.38
    tache
    -0.37
     called
    -0.37
    höhe
    -0.37
    POSITIVE LOGITS
    tvguidetime
    0.82
     intptr
    0.75
    WebVitals
    0.75
     SafeMath
    0.70
    DockStyle
    0.70
     Signalez
    0.69
    ThroughAttribute
    0.69
     EconPapers
    0.67
    NameInMap
    0.67
     StatelessWidget
    0.66
    Activations Density 1.357%

    No Known Activations