© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12926
    Prev
    Next
    INDEX
    Explanations

    the stems of "clean" along with a few miscellaneous words that may be misfires

    oai_token-act-pair · gemini-2.0-flash

    cleaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    zzleHttp
    -0.70
    .
    -0.64
    hical
    -0.64
     sta
    -0.63
     si
    -0.62
     pas
    -0.60
    ,
    -0.60
    finden
    -0.58
     Roh
    -0.57
    ↵↵
    -0.56
    POSITIVE LOGITS
     purpoſe
    1.55
     ſtate
    1.46
     pleaſure
    1.44
     myſelf
    1.44
     greateſt
    1.42
    ſelf
    1.41
     itſelf
    1.40
     houſe
    1.39
     himſelf
    1.38
     uſe
    1.34
    Activations Density 1.645%

    No Known Activations