© 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. 15160
    Prev
    Next
    INDEX
    Explanations

    words related to medicine, confidentiality, spontaneity, speed, ease, and being singular

    oai_token-act-pair · 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
     ExecuteAsync
    -0.68
    }{*}{}
    -0.65
    oglo
    -0.54
     createSlice
    -0.51
    cO
    -0.50
    
    -0.50
    сама
    -0.50
    ąz
    -0.49
    asted
    -0.49
    Bunch
    -0.49
    POSITIVE LOGITS
    فایل‌لار
    0.60
    Portale
    0.57
    orteur
    0.56
     rhestr
    0.51
     raisonnable
    0.51
     kasarigan
    0.49
    RestController
    0.49
     ifrån
    0.48
     än
    0.48
     مرئيه
    0.48
    Activations Density 3.640%

    No Known Activations