© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6181
    Prev
    Next
    INDEX
    Explanations

    mentions of queues

    oai_token-act-pair · gemini-2.0-flash

    queue

    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
     تضيفلها
    -0.92
     BoxFit
    -0.81
     Pute
    -0.75
     Interpolation
    -0.74
    endpush
    -0.74
     newOwner
    -0.73
    podob
    -0.72
     Ceremon
    -0.71
     Adela
    -0.70
     Animations
    -0.69
    POSITIVE LOGITS
     and
    0.84
     but
    0.71
     one
    0.63
     just
    0.61
     or
    0.61
     دیگه
    0.57
    ’
    0.57
     lots
    0.57
     the
    0.56
    beeld
    0.55
    Activations Density 0.794%

    No Known Activations