© 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. 6320
    Prev
    Next
    INDEX
    Explanations

    words and lists related to performances, recordings, and presentations.

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     ſtate
    -0.70
     ftate
    -0.69
     fhort
    -0.68
     Diſ
    -0.65
    iastes
    -0.65
    uxxxx
    -0.62
     fevere
    -0.61
     leſs
    -0.59
    otry
    -0.59
     Reſ
    -0.59
    POSITIVE LOGITS
     number
    0.55
     <=",
    0.50
    number
    0.50
     routine
    0.45
     pas
    0.44
    >{@
    0.44
     numberOf
    0.42
    تقاوى
    0.42
     gesti
    0.42
     Number
    0.42
    Activations Density 5.182%

    No Known Activations