© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9701
    Prev
    Next
    INDEX
    Explanations

    content from internet chat

    oai_token-act-pair · gemini-2.0-flash

    Ubuntu and French

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     الحره
    -0.59
     gynhyrchwyd
    -0.55
     reader
    -0.52
     Bioaccumulative
    -0.50
    ModelSerializer
    -0.50
    GEBURTSDATUM
    -0.50
    JpaRepository
    -0.49
    ThroughAttribute
    -0.48
    ➟
    -0.48
    CommandText
    -0.47
    POSITIVE LOGITS
    Autoritní
    0.57
    bilidad
    0.48
    SDAY
    0.46
    Controllo
    0.43
    trials
    0.43
     Mors
    0.43
     Trustees
    0.42
    Madre
    0.42
     transmitir
    0.42
    principalTable
    0.42
    Activations Density 0.413%

    No Known Activations