© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2922
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to mechanical devices, tools, and processes

    oai_token-act-pair · gemini-2.0-flash

    items related to mechanical devices or components

    np_token-act-pair-logits · gpt-4o-mini

    mechanical devices/systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     للاسماء
    -0.95
     Efq
    -0.84
     purpoſe
    -0.80
     Shakspeare
    -0.80
    __*/
    -0.79
     pleaſure
    -0.79
     houſe
    -0.77
     незавершена
    -0.76
     faſt
    -0.76
     Anſ
    -0.75
    POSITIVE LOGITS
     device
    0.85
     devices
    0.73
     plate
    0.71
     plates
    0.64
     bar
    0.60
     system
    0.59
    devices
    0.58
    device
    0.57
     dispositivo
    0.57
     pad
    0.56
    Activations Density 3.789%

    No Known Activations