© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15773
    Prev
    Next
    INDEX
    Explanations

    words that describe travel or traversing an area

    oai_token-act-pair · gemini-2.0-flash

    journeys, trips, or tours

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    WireFormatLite
    -0.62
    viles
    -0.52
    WebpackPlugin
    -0.50
    uchos
    -0.50
     METHOD
    -0.49
     Référence
    -0.49
     CASES
    -0.48
    ("")]
    -0.48
    ріш
    -0.48
     Method
    -0.46
    POSITIVE LOGITS
    oredCriteria
    0.77
    fjspx
    0.69
     насељу
    0.65
     længere
    0.59
     <=",
    0.59
     CURLOPT
    0.57
    /***/
    0.57
    adaptiveStyles
    0.55
     >=",
    0.53
    Билгалдахарш
    0.53
    Activations Density 1.218%

    No Known Activations