© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1795
    Prev
    Next
    INDEX
    Explanations

    words and phrases often associated with business or tutoring services

    oai_token-act-pair · gemini-2.0-flash

    experts and professionals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    )_/¯
    -0.85
     GoogleFonts
    -0.79
     raiſ
    -0.78
    parsedMessage
    -0.76
    webElementXpaths
    -0.76
     مشارکت‌کنندگان
    -0.74
    Autoritní
    -0.73
     AssemblyTitle
    -0.73
     pleaſure
    -0.71
    antaranya
    -0.69
    POSITIVE LOGITS
     able
    0.55
     experienced
    0.54
     subject
    0.54
     capable
    0.53
     capables
    0.49
     capaces
    0.46
     Star
    0.44
    experienced
    0.43
     ö
    0.42
    rxjs
    0.42
    Activations Density 2.137%

    No Known Activations