© 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. 4217
    Prev
    Next
    INDEX
    Explanations

    the word "limitations", and also the German preposition "zu"

    oai_token-act-pair · gemini-2.0-flash

    limitations

    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
     myſelf
    -0.83
     purpoſe
    -0.82
     cauſe
    -0.81
     reaſon
    -0.79
    ſelf
    -0.74
     pleaſure
    -0.72
     juſ
    -0.72
     to
    -0.71
     groote
    -0.70
     diſt
    -0.69
    POSITIVE LOGITS
     getItemId
    0.75
    argout
    0.75
    databind
    0.71
    ftagPool
    0.71
    forName
    0.70
     BoxDecoration
    0.70
    CloseOperation
    0.69
    QMetaType
    0.69
     doInBackground
    0.68
    addGap
    0.68
    Activations Density 1.417%

    No Known Activations