© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11665
    Prev
    Next
    INDEX
    Explanations

    phrases about life experiences and getting back to the middle

    oai_token-act-pair · gemini-2.0-flash

    references to the concept of 'middle' or 'medium'

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

    middle

    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
    rawDesc
    -0.77
    الحياه
    -0.72
    الإنجليزية
    -0.71
     CURIAM
    -0.67
    المكان
    -0.66
     Infórmanos
    -0.65
    RenderAtEndOf
    -0.65
    calipsis
    -0.64
    LookAnd
    -0.63
    UnitTesting
    -0.63
    POSITIVE LOGITS
     middle
    1.14
     mid
    1.10
    mid
    1.02
     in
    1.01
    middle
    0.93
     medio
    0.85
     MIDDLE
    0.84
     Mid
    0.83
     middel
    0.82
     medium
    0.82
    Activations Density 0.794%

    No Known Activations