© 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. 12692
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to numerical quantities and short durations/distances

    oai_token-act-pair · gemini-2.0-flash

    numbers and measurement

    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
    ReusableCell
    -0.80
     مشين
    -0.79
    RetentionPolicy
    -0.74
    SequentialGroup
    -0.67
    yntaxException
    -0.65
    jspx
    -0.64
     ModelExpression
    -0.61
     AttributeSet
    -0.60
     kaynağından
    -0.60
    ubehör
    -0.60
    POSITIVE LOGITS
    当
    0.45
     dieux
    0.43
    <bos>
    0.41
    ///</
    0.40
     parlant
    0.40
     namelijk
    0.40
     képes
    0.40
    /*
    0.40
     keduanya
    0.39
    當
    0.38
    Activations Density 6.400%

    No Known Activations