© 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. 1611
    Prev
    Next
    INDEX
    Explanations

    bracketed parameters for file formats and dimensions

    oai_token-act-pair · gemini-2.0-flash

    LaTeX code snippets

    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
     الحره
    -0.67
    IBarButtonItem
    -0.60
    StoryboardSegue
    -0.59
    CodedInputStream
    -0.58
    ंदीखरीदारी
    -0.57
     correctes
    -0.56
    SerializedSize
    -0.56
    CloseOperation
    -0.56
    pragma
    -0.56
    IActionResult
    -0.56
    POSITIVE LOGITS
    
    0.59
    <bos>
    0.50
     invokingState
    0.46
     Tengah
    0.46
     conservé
    0.45
     VIDEOTAPE
    0.44
    følgelig
    0.44
     Skelton
    0.43
     réfrig
    0.43
     })
    0.43
    Activations Density 0.146%

    No Known Activations