© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5375
    Prev
    Next
    INDEX
    Explanations

    the word "since" and question marks, possibly indicating reasoning or questions

    oai_token-act-pair · gemini-2.0-flash

    since

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    WriteTagHelper
    -0.86
     &___
    -0.73
    Skocz
    -0.69
    
    -0.68
    ]--;
    -0.66
    icksburg
    -0.63
     AspNetCore
    -0.62
    Externé
    -0.62
     VizieR
    -0.61
     MainAxisSize
    -0.59
    POSITIVE LOGITS
     then
    0.66
     Barth
    0.55
    fortawesome
    0.52
    createObject
    0.52
    ="{{$
    0.50
     erlang
    0.50
     MongoClient
    0.48
    PDOException
    0.46
     THEN
    0.46
     nonatomic
    0.46
    Activations Density 2.670%

    No Known Activations