© 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. 5140
    Prev
    Next
    INDEX
    Explanations

    text discussing electrical engineering and related problem-solving using components like resistors and sensors

    oai_token-act-pair · gemini-2.0-flash

    electronic circuits/signals

    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
     leher
    -0.55
     kele
    -0.54
    tagHelperRunner
    -0.50
    kapat
    -0.50
    __(/*!
    -0.49
     karyawan
    -0.49
     hran
    -0.48
     مقاط
    -0.47
     Staff
    -0.47
     umur
    -0.47
    POSITIVE LOGITS
     myſelf
    0.88
     itſelf
    0.82
     Theſe
    0.81
    OrNil
    0.80
     Diſ
    0.77
     againſt
    0.77
    AutoScaleMode
    0.77
     referenties
    0.75
     pleaſure
    0.75
    aarrggbb
    0.73
    Activations Density 5.735%

    No Known Activations