© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5475
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to electronic connections and descriptive words which come before a noun

    oai_token-act-pair · gemini-2.0-flash

    tapping/accessing, bay area

    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
     Theſe
    -1.09
     Eſ
    -1.05
     itſelf
    -1.00
     Jefus
    -0.97
     Monfieur
    -0.93
    ſelf
    -0.93
     whoſe
    -0.93
     Efq
    -0.91
     Diſ
    -0.90
     Reſ
    -0.90
    POSITIVE LOGITS
    SequentialGroup
    0.74
    currentColor
    0.69
    Controllo
    0.69
     gainera
    0.67
    WebVitals
    0.65
     '\\;'
    0.64
     Lovato
    0.63
     Obrador
    0.63
    cault
    0.62
     оригіналу
    0.61
    Activations Density 1.907%

    No Known Activations