© 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. 14616
    Prev
    Next
    INDEX
    Explanations

    words associated with outcomes, either positive or negative.

    oai_token-act-pair · gemini-2.0-flash

    prevail, root

    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
    Hentet
    -0.63
    rativo
    -0.54
     meur
    -0.53
    ActionCreators
    -0.52
    aurus
    -0.52
    ärna
    -0.51
    München
    -0.51
     vägen
    -0.50
    — 
    -0.50
    andidaten
    -0.50
    POSITIVE LOGITS
     estekak
    0.58
     prevailed
    0.51
     prevail
    0.51
     ExecuteAsync
    0.51
    Referències
    0.51
     setMessage
    0.50
    चे
    0.49
    UrlResolution
    0.49
     prevails
    0.48
    NewUrlParser
    0.46
    Activations Density 2.812%

    No Known Activations