© 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. 12671
    Prev
    Next
    INDEX
    Explanations

    very generic filler words and punctuation, suggesting a failure to learn properly

    oai_token-act-pair · gemini-2.0-flash

    addressing problems

    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
    AddTagHelper
    -1.05
    tagHelperRunner
    -1.01
     ویکی‌پدی
    -0.99
    <bos>
    -0.98
    تقاوى
    -0.96
     Taktlose
    -0.94
     Roskov
    -0.94
    GEBURTSDATUM
    -0.93
     propOrder
    -0.91
    ConstraintMaker
    -0.91
    POSITIVE LOGITS
     optional
    0.45
    ”
    0.45
    </em>
    0.43
    ku
    0.43
    kus
    0.43
     style
    0.42
     combinaison
    0.42
     combination
    0.42
     common
    0.41
    way
    0.41
    Activations Density 0.506%

    No Known Activations