© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11744
    Prev
    Next
    INDEX
    Explanations

    words related to finding, assessing, and questioning evidence in analytical scenarios

    oai_token-act-pair · gemini-2.0-flash

    impact/effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     betweenstory
    -0.88
     cauſe
    -0.56
     pleaſure
    -0.55
    
    -0.53
    óż
    -0.53
    Atsauces
    -0.52
     Inequalities
    -0.51
     nickname
    -0.51
     propOrder
    -0.50
     cesar
    -0.48
    POSITIVE LOGITS
     Infórmanos
    0.69
    MessageTagHelper
    0.61
     Signalez
    0.61
    PreExecute
    0.60
    MemoryWarning
    0.54
    jspx
    0.54
     actionTypes
    0.53
    BagLayout
    0.52
     ...
    0.52
    Dtor
    0.52
    Activations Density 2.317%

    No Known Activations